|
neuralnet |
Introduction to the use of neural networks |
7 hours |
Szkolenie skierowane jest do osób, które chcą zapoznać się z podstawami sieci neuronowych oraz ich zastosowań.
Podstawy
-
Czy komputery mogą myśleć?
-
Podejście deklaratywne i imperatywne do rozwiązywania problemów
-
Cel bedań nad sztuczna inteligencją
-
Definicja sztucznej inteligencji. Test Turinga. Inne wyznaczniki
-
Rozwój koncepcji inteligentnych systemów
-
Najważniejsze osiągniącia i kierunki rozwoju
Sieci neuronowe
-
Podstawy
-
Koncepcja neuronu i sieci neuronowych
-
Uproszczony model mózgu
-
Możliwości neuronu
-
Problem XOR i charakter podziału wartości
-
Polimorficzny charakter funkcji sigmoidalnej
-
Pozostałe funkcje aktywacji
-
Budowa sieci neuronowych
-
Koncepcja łączenie neuronów
-
Sieć neuronowa jako węzły
-
Budowa sieci
-
Neurony
-
Warstwy
-
Wagi
-
Dane wejściowe i wyjściowe
-
Zakresy 0..1
-
Normalizacja
-
Uczenie sieci neuronowych
-
Propagacja wsteczna
-
Kroki propagacji
-
Algorytmy uczenia sieci
-
Zakres zastosowań
-
Estymacja
-
Problemy z możliwością przybliżenia wyniku
-
Przykłady
-
Problem XOR
-
Totolotek?
-
Kursy akcji
-
OCR i rozpoznawanie wzorów obrazów
-
Inne zastosowania
-
Modelowanie sieci neuronowej realizującej zadanie przewidywania kursów akcji giełdowych
Problemy na dziś
-
Eksplocja kombinatoryczna i problemy gier
-
Test Turinga raz jeszcze
-
Zbytnia ufność w możliwości komputerów
|
|
datamodeling |
Pattern Recognition |
35 hours |
This course provides an introduction into the field of pattern recognition and machine learning. It touches on practical applications in statistics, computer science, signal processing, computer vision, data mining, and bioinformatics.
The course is interactive and includes plenty of hands-on exercises, instructor feedback, and testing of knowledge and skills acquired.
Audience
Data analysts
PhD students, researchers and practitioners
Introduction
Probability theory, model selection, decision and information theory
Probability distributions
Linear models for regression and classification
Neural networks
Kernel methods
Sparse kernel machines
Graphical models
Mixture models and EM
Approximate inference
Sampling methods
Continuous latent variables
Sequential data
Combining models
|
|
rneuralnet |
Sieci Neuronowe w R |
14 hours |
Szkolenie jest wprowadzeniem do wdrożenia sieci neuronowych w życiu codziennym wykorzystując oprogramowanie R-project. Introduction to Neural Networks
- What are Neural Networks
- What is current status in applying neural networks
- Neural Networks vs regression models
- Supervised and Unsupervised learning
Overview of packages available
- nnet, neuralnet and others
- differences between packages and itls limitations
- Visualizing neural networks
Applying Neural Networks
- Concept of neurons and neural networks
- A simplified model of the brain
- Opportunities neuron
- XOR problem and the nature of the distribution of values
- The polymorphic nature of the sigmoidal
- Other functions activated
- Construction of neural networks
- Concept of neurons connect
- Neural network as nodes
- Building a network
- Neurons
- Layers
- Scales
- Input and output data
- Range 0 to 1
- Normalization
- Learning Neural Networks
- Backward Propagation
- Steps propagation
- Network training algorithms
- range of application
- Estimation
- Problems with the possibility of approximation by
- Examples
- OCR and image pattern recognition
- Other applications
- Implementing a neural network modeling job predicting stock prices of listed
|
|
Torch |
Torch: Getting started with Machine and Deep Learning |
21 hours |
Torch is an open source machine learning library and a scientific computing framework based on the Lua programming language. It provides a development environment for numerics, machine learning, and computer vision, with a particular emphasis on deep learning and convolutional nets. It is one of the fastest and most flexible frameworks for Machine and Deep Learning and is used by companies such as Facebook, Google, Twitter, NVIDIA, AMD, Intel, and many others.
In this course we cover the principles of Torch, its unique features, and how it can be applied in real-world applications. We step through numerous hands-on exercises all throughout, demonstrating and practicing the concepts learned.
By the end of the course, participants will have a thorough understanding of Torch's underlying features and capabilities as well as its role and contribution within the AI space compared to other frameworks and libraries. Participants will have also received the necessary practice to implement Torch in their own projects.
Audience
Software developers and programmers wishing to enable Machine and Deep Learning within their applications
Format of the course
Overview of Machine and Deep Learning
In-class coding and integration exercises
Test questions sprinkled along the way to check understanding
Introduction to Torch
Like NumPy but with CPU and GPU implementation
Torch's usage in machine learning, computer vision, signal processing, parallel processing, image, video, audio and networking
Installing Torch
Linux, Windows, Mac
Bitmapi and Docker
Installing Torch packages
Using the LuaRocks package manager
Choosing an IDE for Torch
ZeroBrane Studio
Eclipse plugin for Lua
Working with the Lua scripting language and LuaJIT
Lua's integration with C/C++
Lua syntax: datatypes, loops and conditionals, functions, functions, tables, and file i/o.
Object orientation and serialization in Torch
Coding exercise
Loading a dataset in Torch
MNIST
CIFAR-10, CIFAR-100
Imagenet
Machine Learning in Torch
Deep Learning
Manual feature extraction vs convolutional networks
Supervised and Unsupervised Learning
Building a neural network with Torch
N-dimensional arrays
Image analysis with Torch
Image package
The Tensor library
Working with the REPL interpreter
Working with databases
Networking and Torch
GPU support in Torch
Integrating Torch
C, Python, and others
Embedding Torch
iOS and Android
Other frameworks and libraries
Facebook's optimized deep-learning modules and containers
Creating your own package
Testing and debugging
Releasing your application
The future of AI and Torch
|
|
MLFWR1 |
Machine Learning Fundamentals with R |
14 hours |
The aim of this course is to provide a basic proficiency in applying Machine Learning methods in practice. Through the use of the R programming platform and its various libraries, and based on a multitude of practical examples this course teaches how to use the most important building blocks of Machine Learning, how to make data modeling decisions, interpret the outputs of the algorithms and validate the results.
Our goal is to give you the skills to understand and use the most fundamental tools from the Machine Learning toolbox confidently and avoid the common pitfalls of Data Sciences applications.
Introduction to Applied Machine Learning
- Statistical learning vs. Machine learning
- Iteration and evaluation
- Bias-Variance trade-off
Regression
- Linear regression
- Generalizations and Nonlinearity
- Exercises
Classification
- Bayesian refresher
- Naive Bayes
- Logistic regression
- K-Nearest neighbors
- Exercises
Cross-validation and Resampling
- Cross-validation approaches
- Bootstrap
- Exercises
Unsupervised Learning
- K-means clustering
- Examples
- Challenges of unsupervised learning and beyond K-means
|
|
OpenNN |
OpenNN: Implementing neural networks |
14 hours |
OpenNN is an open-source class library written in C++ which implements neural networks, for use in machine learning.
In this course we go over the principles of neural networks and use OpenNN to implement a sample application.
Audience
Software developers and programmers wishing to create Deep Learning applications.
Format of the course
Lecture and discussion coupled with hands-on exercises.
Introduction to OpenNN, Machine Learning and Deep Learning
Downloading OpenNN
Working with Neural Designer
Using Neural Designer for descriptive, diagnostic, predictive and prescriptive analytics
OpenNN architecture
CPU parallelization
OpenNN classes
Data set, neural network, loss index, training strategy, model selection, testing analysis
Vector and matrix templates
Building a neural network application
Choosing a suitable neural network
Formulating the variational problem (loss index)
Solving the reduced function optimization problem (training strategy)
Working with datasets
The data matrix (columns as variables and rows as instances)
Learning tasks
Function regression
Pattern recognition
Compiling with QT Creator
Integrating, testing and debugging your application
The future of neural networks and OpenNN
|
|
appliedml |
Applied Machine Learning |
14 hours |
This training course is for people that would like to apply Machine Learning in practical applications.
Audience
This course is for data scientists and statisticians that have some familiarity with statistics and know how to program R (or Python or other chosen language). The emphasis of this course is on the practical aspects of data/model preparation, execution, post hoc analysis and visualization.
The purpose is to give practical applications to Machine Learning to participants interested in applying the methods at work.
Sector specific examples are used to make the training relevant to the audience.
- Naive Bayes
- Multinomial models
- Bayesian categorical data analysis
- Discriminant analysis
- Linear regression
- Logistic regression
- GLM
- EM Algorithm
- Mixed Models
- Additive Models
- Classification
- KNN
- Bayesian Graphical Models
- Factor Analysis (FA)
- Principal Component Analysis (PCA)
- Independent Component Analysis (ICA)
- Support Vector Machines (SVM) for regression and classification
- Boosting
- Ensemble models
- Neural networks
- Hidden Markov Models (HMM)
- Space State Models
- Clustering
|
|
mldt |
Machine Learning and Deep Learning |
21 hours |
This course covers AI (emphasizing Machine Learning and Deep Learning)
Machine learning
Introduction to Machine Learning
-
Applications of machine learning
-
Supervised Versus Unsupervised Learning
-
Machine Learning Algorithms
-
Regression
-
Classification
-
Clustering
-
Recommender System
-
Anomaly Detection
-
Reinforcement Learning
Regression
Resampling Methods
-
Cross-Validation
-
The Validation Set Approach
-
Leave-One-Out Cross-Validation
-
k-Fold Cross-Validation
-
Bias-Variance Trade-Off for k-Fold
-
The Bootstrap
Model Selection and Regularization
-
Subset Selection [Best Subset Selection, Stepwise Selection, Choosing the Optimal Model]
-
Shrinkage Methods/ Regularization [Ridge Regression, Lasso & Elastic Net]
-
Selecting the Tuning Parameter
-
Dimension Reduction Methods
Classification
-
Logistic Regression
-
The Logistic Model cost function
-
Estimating the Coefficients
-
Making Predictions
-
Odds Ratio
-
Performance Evaluation Matrices
-
[Sensitivity/Specificity/PPV/NPV, Precision, ROC curve etc.]
-
Multiple Logistic Regression
-
Logistic Regression for >2 Response Classes
-
Regularized Logistic Regression
-
Linear Discriminant Analysis
-
Using Bayes’ Theorem for Classification
-
Linear Discriminant Analysis for p=1
-
Linear Discriminant Analysis for p >1
-
Quadratic Discriminant Analysis
-
K-Nearest Neighbors
-
Classification with Non-linear Decision Boundaries
-
Support Vector Machines
-
Optimization Objective
-
The Maximal Margin Classifier
-
Kernels
-
One-Versus-One Classification
-
One-Versus-All Classification
-
Comparison of Classification Methods
Introduction to Deep Learning
ANN Structure
-
Biological neurons and artificial neurons
-
Non-linear Hypothesis
-
Model Representation
-
Examples & Intuitions
-
Transfer Function/ Activation Functions
-
Typical classes of network architectures
Feed forward ANN.
-
Structures of Multi-layer feed forward networks
-
Back propagation algorithm
-
Back propagation - training and convergence
-
Functional approximation with back propagation
-
Practical and design issues of back propagation learning
Deep Learning
Lab:
Getting Started with R
-
Introduction to R
-
Basic Commands & Libraries
-
Data Manipulation
-
Importing & Exporting data
-
Graphical and Numerical Summaries
-
Writing functions
Regression
-
Simple & Multiple Linear Regression
-
Interaction Terms
-
Non-linear Transformations
-
Dummy variable regression
-
Cross-Validation and the Bootstrap
-
Subset selection methods
-
Penalization [Ridge, Lasso, Elastic Net]
Classification
-
Logistic Regression, LDA, QDA, and KNN,
-
Resampling & Regularization
-
Support Vector Machine
-
Resampling & Regularization
Note:
-
For ML algorithms, case studies will be used to discuss their application, advantages & potential issues.
-
Analysis of different data sets will be performed using R
|
|
mlintro |
Introduction to Machine Learning |
7 hours |
This training course is for people that would like to apply basic Machine Learning techniques in practical applications.
Audience
Data scientists and statisticians that have some familiarity with machine learning and know how to program R. The emphasis of this course is on the practical aspects of data/model preparation, execution, post hoc analysis and visualization. The purpose is to give a practical introduction to machine learning to participants interested in applying the methods at work
Sector specific examples are used to make the training relevant to the audience.
- Naive Bayes
- Multinomial models
- Bayesian categorical data analysis
- Discriminant analysis
- Linear regression
- Logistic regression
- GLM
- EM Algorithm
- Mixed Models
- Additive Models
- Classification
- KNN
- Ridge regression
- Clustering
|
|
opennmt |
OpenNMT: Setting up a Neural Machine Translation system |
7 hours |
OpenNMT is a full-featured, open-source (MIT) neural machine translation system that utilizes the Torch mathematical toolkit.
In this training participants will learn how to set up and use OpenNMT to carry out translation of various sample data sets. The course starts with an overview of neural networks as they apply to machine translation. Participants will carry out live exercises throughout the course to demonstrate their understanding of the concepts learned and get feedback from the instructor. By the end of this training, participants will have the knowledge and practice needed to implement a live OpenNMT solution.
Source and target language samples will be pre-arranged per the audience's requirements.
Audience
- Localization specialists with a technical background
- Global content managers
- Localization engineers
- Software developers in charge of implementing global content solutions
Format of the course
- Part lecture, part discussion, heavy hands-on practice
Introduction
Why Neural Machine Translation?
Overview of the Torch project
Installation and setup
Preprocessing your data
Training the model
Translating
Using pre-trained models
Working with Lua scripts
Using extensions
Troubleshooting
Joining the community
Closing remarks
|
|
d2dbdpa |
From Data to Decision with Big Data and Predictive Analytics |
21 hours |
Audience
If you try to make sense out of the data you have access to or want to analyse unstructured data available on the net (like Twitter, Linked in, etc...) this course is for you.
It is mostly aimed at decision makers and people who need to choose what data is worth collecting and what is worth analyzing.
It is not aimed at people configuring the solution, those people will benefit from the big picture though.
Delivery Mode
During the course delegates will be presented with working examples of mostly open source technologies.
Short lectures will be followed by presentation and simple exercises by the participants
Content and Software used
All software used is updated each time the course is run so we check the newest versions possible.
It covers the process from obtaining, formatting, processing and analysing the data, to explain how to automate decision making process with machine learning.
Quick Overview
- Data Sources
- Minding Data
- Recommender systems
- Target Marketing
Datatypes
- Structured vs unstructured
- Static vs streamed
- Attitudinal, behavioural and demographic data
- Data-driven vs user-driven analytics
- data validity
- Volume, velocity and variety of data
Models
- Building models
- Statistical Models
- Machine learning
Data Classification
- Clustering
- kGroups, k-means, nearest neighbours
- Ant colonies, birds flocking
Predictive Models
- Decision trees
- Support vector machine
- Naive Bayes classification
- Neural networks
- Markov Model
- Regression
- Ensemble methods
ROI
- Benefit/Cost ratio
- Cost of software
- Cost of development
- Potential benefits
Building Models
- Data Preparation (MapReduce)
- Data cleansing
- Choosing methods
- Developing model
- Testing Model
- Model evaluation
- Model deployment and integration
Overview of Open Source and commercial software
- Selection of R-project package
- Python libraries
- Hadoop and Mahout
- Selected Apache projects related to Big Data and Analytics
- Selected commercial solution
- Integration with existing software and data sources
|
|
Fairsec |
Fairsec: Setting up a CNN-based machine translation system |
7 hours |
Fairseq is an open-source sequence-to-sequence learning toolkit created by Facebok for use in Neural Machine Translation (NMT).
In this training participants will learn how to use Fairseq to carry out translation of sample content. By the end of this training, participants will have the knowledge and practice needed to implement a live Fairseq based machine translation solution. Source and target language content samples can be prepared according to audience's requirements.
Audience
- Localization specialists with a technical background
- Global content managers
- Localization engineers
- Software developers in charge of implementing global content solutions
Format of the course
Part lecture, part discussion, heavy hands-on practice
Introduction
Why Neural Machine Translation?
Overview of the Torch project
Overview of a Convolutional Neural Machine Translation model
Convolutional Sequence to Sequence Learning
Convolutional Encoder Model for Neural Machine Translation
Standard LSTM-based model
Overview of training approaches
About GPUs and CPUs
Fast beam search generation
Installation and setup
Evaluating pre-trained models
Preprocessing your data
Training the model
Translating
Converting a trained model to use CPU-only operations
Joining to the community
Closing remarks
|
|
annmldt |
Artificial Neural Networks, Machine Learning, Deep Thinking |
21 hours |
DAY 1 - ARTIFICIAL NEURAL NETWORKS
Introduction and ANN Structure.
- Biological neurons and artificial neurons.
- Model of an ANN.
- Activation functions used in ANNs.
- Typical classes of network architectures .
Mathematical Foundations and Learning mechanisms.
- Re-visiting vector and matrix algebra.
- State-space concepts.
- Concepts of optimization.
- Error-correction learning.
- Memory-based learning.
- Hebbian learning.
- Competitive learning.
Single layer perceptrons.
- Structure and learning of perceptrons.
- Pattern classifier - introduction and Bayes' classifiers.
- Perceptron as a pattern classifier.
- Perceptron convergence.
- Limitations of a perceptrons.
Feedforward ANN.
- Structures of Multi-layer feedforward networks.
- Back propagation algorithm.
- Back propagation - training and convergence.
- Functional approximation with back propagation.
- Practical and design issues of back propagation learning.
Radial Basis Function Networks.
- Pattern separability and interpolation.
- Regularization Theory.
- Regularization and RBF networks.
- RBF network design and training.
- Approximation properties of RBF.
Competitive Learning and Self organizing ANN.
- General clustering procedures.
- Learning Vector Quantization (LVQ).
- Competitive learning algorithms and architectures.
- Self organizing feature maps.
- Properties of feature maps.
Fuzzy Neural Networks.
- Neuro-fuzzy systems.
- Background of fuzzy sets and logic.
- Design of fuzzy stems.
- Design of fuzzy ANNs.
Applications
- A few examples of Neural Network applications, their advantages and problems will be discussed.
DAY -2 MACHINE LEARNING
- The PAC Learning Framework
- Guarantees for finite hypothesis set – consistent case
- Guarantees for finite hypothesis set – inconsistent case
- Generalities
- Deterministic cv. Stochastic scenarios
- Bayes error noise
- Estimation and approximation errors
- Model selection
- Radmeacher Complexity and VC – Dimension
- Bias - Variance tradeoff
- Regularisation
- Over-fitting
- Validation
- Support Vector Machines
- Kriging (Gaussian Process regression)
- PCA and Kernel PCA
- Self Organisation Maps (SOM)
- Kernel induced vector space
- Mercer Kernels and Kernel - induced similarity metrics
- Reinforcement Learning
DAY 3 - DEEP LEARNING
This will be taught in relation to the topics covered on Day 1 and Day 2
- Logistic and Softmax Regression
- Sparse Autoencoders
- Vectorization, PCA and Whitening
- Self-Taught Learning
- Deep Networks
- Linear Decoders
- Convolution and Pooling
- Sparse Coding
- Independent Component Analysis
- Canonical Correlation Analysis
- Demos and Applications
|
|
Fairseq |
Fairseq: Setting up a CNN-based machine translation system |
7 hours |
Fairseq is an open-source sequence-to-sequence learning toolkit created by Facebok for use in Neural Machine Translation (NMT).
In this training participants will learn how to use Fairseq to carry out translation of sample content. By the end of this training, participants will have the knowledge and practice needed to implement a live Fairseq based machine translation solution. Source and target language content samples can be prepared according to audience's requirements.
Audience
- Localization specialists with a technical background
- Global content managers
- Localization engineers
- Software developers in charge of implementing global content solutions
Format of the course
Part lecture, part discussion, heavy hands-on practice
Introduction
Why Neural Machine Translation?
Overview of the Torch project
Overview of a Convolutional Neural Machine Translation model
Convolutional Sequence to Sequence Learning
Convolutional Encoder Model for Neural Machine Translation
Standard LSTM-based model
Overview of training approaches
About GPUs and CPUs
Fast beam search generation
Installation and setup
Evaluating pre-trained models
Preprocessing your data
Training the model
Translating
Converting a trained model to use CPU-only operations
Joining to the community
Closing remarks
|
|
deeplearning1 |
Introduction to Deep Learning |
21 hours |
This course is general overview for Deep Learning without going too deep into any specific methods. It is suitable for people who want to start using Deep learning to enhance their accuracy of prediction.
- Backprop, modular models
- Logsum module
- RBF Net
- MAP/MLE loss
- Parameter Space Transforms
- Convolutional Module
-
Gradient-Based Learning
-
Energy for inference,
-
Objective for learning
-
PCA; NLL:
- Latent Variable Models
- Probabilistic LVM
- Loss Function
- Handwriting recognition
|
|
facebooknmt |
Facebook NMT: Setting up a neural machine translation system |
7 hours |
Fairseq is an open-source sequence-to-sequence learning toolkit created by Facebok for use in Neural Machine Translation (NMT).
In this training participants will learn how to use Fairseq to carry out translation of sample content.
By the end of this training, participants will have the knowledge and practice needed to implement a live Fairseq based machine translation solution.
Audience
- Localization specialists with a technical background
- Global content managers
- Localization engineers
- Software developers in charge of implementing global content solutions
Format of the course
- Part lecture, part discussion, heavy hands-on practice
Note
- If you wish to use specific source and target language content, please contact us to arrange.
Introduction
Why Neural Machine Translation?
Borrowing from image recognition techniques
Overview of the Torch and Caffe2 projects
Overview of a Convolutional Neural Machine Translation model
Convolutional Sequence to Sequence Learning
Convolutional Encoder Model for Neural Machine Translation
Standard LSTM-based model
Overview of training approaches
About GPUs and CPUs
Fast beam search generation
Installation and setup
Evaluating pre-trained models
Preprocessing your data
Training the model
Translating
Converting a trained model to use CPU-only operations
Joining to the community
Closing remarks
|
|
sysagent |
Systemy wieloagentowe |
7 hours |
1. Wstęp systemy wieloagentowe
a. czym jest agent programowy
b. rodzaje agentów
c. platformawieloagentowa i społeczność agentów
d. analogia do systemów żywych
2. Teoria
a. Architektury systemów wieloagentowych
- architektury logiczne
- architektury reaktywne
- architektury BDI (belief, desires, intentions)
- architektury AGR (Agent/Group/Role)
- inne architektury
b. Inteligencja agenta i interakcja z otoczeniem
- pozyskiwanie i gromadzenie wiedzy
- interakcja ze środowiskiem w którym funkcjonuje agent
- komunikacja i interakcja z innymi agentami (wymiana wiedzy)
- rozwiązywanie konfliktów (negocjacje)
- planowanie i podejmowanie decyzji
c. Wybrane algorytmy społecznościowe
- kolonia mrówek
- stado (ławica, rój cząstek)
|
|
tpuprogramming |
TPU Programming: Building Neural Network Applications on Tensor Processing Units |
7 hours |
The Tensor Processing Unit (TPU) is the architecture which Google has used internally for several years, and is just now becoming available for use by the general public. It includes several optimizations specifically for use in neural networks, including streamlined matrix multiplication, and 8-bit integers instead of 16-bit in order to return appropriate levels of precision.
In this instructor-led, live training, participants will learn how to take advantage of the innovations in TPU processors to maximize the performance of their own AI applications.
By the end of the training, participants will be able to:
- Train various types of neural networks on large amounts of data
- Use TPUs to speed up the inference process by up to two orders of magnitude
- Utilize TPUs to process intensive applications such as image search, cloud vision and photos
Audience
- Developers
- Researchers
- Engineers
- Data scientists
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
To request a customized course outline for this training, please contact us.
|
|
pjn |
Przetwarzanie języka naturalnego |
7 hours |
1. Wprowadzenie
2. Zastosowania NLP
- Podstawowe pojęcia
- Narzędzia NLP
3. Podstawy języka Perl
- Struktury danych
- Wyrażenia regularne
- Parsowanie i tokenizacja
4 . Podstawy narzędzi RDBMS
- Pająki internetowe
- Korpus tekstowy
- Własności statystyczne
- Listy stopsłów
- Indeksowanie dokumentów
5. Wyszukiwarka dokumentów
- analiza leksykalna
- wyszukiwanie wzorca
- słowniki i automaty słownikowe
- analiza morfologiczna
- techniki ngramów
- podobieństwo dokumentów
|
|
MicrosoftCognitiveToolkit |
Microsoft Cognitive Toolkit 2.x |
21 hours |
Microsoft Cognitive Toolkit 2.x (previously CNTK) is an open-source, commercial-grade toolkit that trains deep learning algorithms to learn like the human brain. According to Microsoft, CNTK can be 5-10x faster than TensorFlow on recurrent networks, and 2 to 3 times faster than TensorFlow for image-related tasks.
In this instructor-led, live training, participants will learn how to use Microsoft Cognitive Toolkit to create, train and evaluate deep learning algorithms for use in commercial-grade AI applications involving multiple types of data such data, speech, text, and images.
By the end of this training, participants will be able to:
- Access CNTK as a library from within a Python, C#, or C++ program
- Use CNTK as a standalone machine learning tool through its own model description language (BrainScript)
- Use the CNTK model evaluation functionality from a Java program
- Combine feed-forward DNNs, convolutional nets (CNNs), and recurrent networks (RNNs/LSTMs)
- Scale computation capacity on CPUs, GPUs and multiple machines
- Access massive datasets using existing programming languages and algorithms
Audience
- Developers
- Data scientists
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
Note
- If you wish to customize any part of this training, including the programming language of choice, please contact us to arrange.
To request a customized course outline for this training, please contact us.
|
|
iop |
Inteligencja obliczeniowa w praktyce |
7 hours |
1. Obszary zastosowań
- klasyfikacja (metody jakościowe, np. WTA)
- regresja (metody ilościowe, np. próg decyzyjny)
2. Surowe dane
3. Przetwarzanie wstępne danych, sygnałów (np. normalizacja, PCA, FFT itp.)
4. Dobór elementów do zbioru uczącego i testowego (np. walidacja krzyżowa)
5. Wybór metody inteligencji obliczeniowej
6. Optymalizacja parametrów treningu (np. algorytmy genetyczne)
7. Ocena uzyskanych wyników (np. krzywa ROC)
8. Przykładowe zastosowania MIO:
- rozpoznawanie osób na podstawie gestów z ekranu
- rozpoznawanie gestów, ruchów dłonią
- identyfikacja rodzaju atramentu i papieru
- diagnozowanie dysfunkcji mięśnia sercowego
- analiza lotnych związków organicznych przy użyciu elektronicznego nosa (klasyfikacja gatunków herbaty i aproksymacja stężenia fenolu)
- szacowanie wypracowania pompy wyporowej
|
|
snorkel |
Snorkel: Rapidly process training data |
7 hours |
Snorkel is a system for rapidly creating, modeling, and managing training data. It focuses on accelerating the development of structured or "dark" data extraction applications for domains in which large labeled training sets are not available or easy to obtain.
In this instructor-led, live training, participants will learn techniques for extracting value from unstructured data such as text, tables, figures, and images through modeling of training data with Snorkel.
By the end of this training, participants will be able to:
- Programmatically create training sets to enable the labeling of massive training sets
- Train high-quality end models by first modeling noisy training sets
- Use Snorkel to implement weak supervision techniques and apply data programming to weakly-supervised machine learning systems
Audience
- Developers
- Data scientists
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
To request a customized course outline for this training, please contact us.
|
|
mtdintob |
Metody Inteligencji Obliczeniowej |
7 hours |
1. Wstęp Sztuczna inteligencja
a. słaba i silna sztuczna inteligencja
b. sztuczna inteligencja a inteligencja obliczeniowa
c. klasyfikacja metod inteligencji obliczeniowej
d. analogie do systemów żywych
2. Metody inteligencji obliczeniowej
a. sztuczne sieci neuronowe
- klasyfikacja i typy sieci neuronowych
- model sztucznego neuronu
- topologia
- metody i algorytmy uczenia
- sieci neuronowe: SOM, MLP, PNN, LVQ, RNN, RBF, GRNN
b. systemy rozmyte
- logika rozmyta
- zbiory rozmyte i funkcje przynależności
- wnioskowanie przybliżone
- zasada działania
- model Mamdani i Sugeno
c. maszyna wektorów nośnych
- zasada działania
- typy funkcji jądra
- typy wielokrotnej klasyfikacji
- mocne i słabe strony
d. obliczenia ewolucyjne
- algorytmy genetyczne
- metody selekcji
- skalowanie funkcji przystosowania
- operatory genetyczne
- porównanie algorytmów ewolucyjnych
e. inteligencja roju
f. inteligentne agenty
g. algorytm knajbliższych sąsiadów
h. systemy hybrydowe
- ewolucyjnoneuronowe
- neuronoworozmyte
- ewolucyjnorozmyte
|
|
encogintro |
Encog: Introduction to Machine Learning |
14 hours |
Encog is an open-source machine learning framework for Java and .Net.
In this instructor-led, live training, participants will learn how to create various neural network components using ENCOG. Real-world case studies will be discussed and machine language based solutions to these problems will be explored.
By the end of this training, participants will be able to:
- Prepare data for neural networks using the normalization process
- Implement feed forward networks and propagation training methodologies
- Implement classification and regression tasks
- Model and train neural networks using Encog's GUI based workbench
- Integrate neural network support into real-world applications
Audience
- Developers
- Analysts
- Data scientists
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
To request a customized course outline for this training, please contact us.
|
|
cntk |
Using Computer Network ToolKit (CNTK) |
28 hours |
Computer Network ToolKit (CNTK) is Microsoft's Open Source, Multi-machine, Multi-GPU, Highly efficent RNN training machine learning framework for speech, text, and images.
Audience
This course is directed at engineers and architects aiming to utilize CNTK in their projects.
Getting started
- Setup CNTK on your machine
- Enabling 1bit SGD
- Developing and Testing
- CNTK Production Test Configurations
- How to contribute to CNTK
- Tutorial
- Tutorial II
- CNTK usage overview
- Examples
- Presentations
- Multiple GPUs¹ and machines
Configuring CNTK
- Config file overview
- Simple Network Builder
- BrainScript Network Builder
- SGD block
- Reader block
- Train, Test, Eval
- Top-level configurations
Describing Networks
- Basic concepts
- Expressions
- Defining functions
- Full Function Reference
Data readers
- Text Format Reader
- CNTK Text Format Reader
- UCI Fast Reader (deprecated)
- HTKMLF Reader
- LM sequence reader
- LU sequence reader
- Image reader
Evaluating CNTK Models
- Overview
- C++ Evaluation Interface
- C# Evaluation Interface
- Evaluating Hidden Layers
- C# Image Transforms for Evaluation
Advanced topics
- Command line parsing rules
- Top-level commands
- Plot command
- ConvertDBN command
¹ The topic related to the use of CNTK with a GPU is not available as a part of a remote course. This module can be delivered during classroom-based courses, but only by prior agreement, and only if both the trainer and all participants have laptops with supported NVIDIA GPUs (not provided by NobleProg). NobleProg cannot guarantee the availability of trainers with the required hardware. |
|
encogadv |
Encog: Advanced Machine Learning |
14 hours |
Encog is an open-source machine learning framework for Java and .Net.
In this instructor-led, live training, participants will learn advanced machine learning techniques for building accurate neural network predictive models.
By the end of this training, participants will be able to:
- Implement different neural networks optimization techniques to resolve underfitting and overfitting
- Understand and choose from a number of neural network architectures
- Implement supervised feed forward and feedback networks
Audience
- Developers
- Analysts
- Data scientists
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
To request a customized course outline for this training, please contact us.
|
|
aiintrozero |
From Zero to AI |
35 hours |
This course is created for people who have no previous experience in probability and statistics.
Probability (3.5h)
- Definition of probability
- Binomial distribution
- Everyday usage exercises
Statistics (10.5h)
- Descriptive Statistics
- Inferential Statistics
- Regression
- Logistic Regression
- Exercises
Intro to programming (3.5h)
- Procedural Programming
- Functional Programming
- OOP Programming
- Exercises (writing logic for a game of choice, e.g. noughts and crosses)
Machine Learning (10.5h)
- Classification
- Clustering
- Neural Networks
- Exercises (write AI for a computer game of choice)
Rules Engines and Expert Systems (7 hours)
- Intro to Rule Engines
- Write AI for the same game and combine solutions into hybrid approach
|
|
aiauto |
Artificial Intelligence in Automotive |
14 hours |
This course covers AI (emphasizing Machine Learning and Deep Learning) in Automotive Industry. It helps to determine which technology can be (potentially) used in multiple situation in a car: from simple automation, image recognition to autonomous decision making.
Current state of the technology
- What is used
- What may be potentially used
Rules based AI
Machine Learning
- Classification
- Clustering
- Neural Networks
- Types of Neural Networks
- Presentation of working examples and discussion
Deep Learning
- Basic vocabulary
- When to use Deep Learning, when not to
- Estimating computational resources and cost
- Very short theoretical background to Deep Neural Networks
Deep Learning in practice (mainly using TensorFlow)
- Preparing Data
- Choosing loss function
- Choosing appropriate type on neural network
- Accuracy vs speed and resources
- Training neural network
- Measuring efficiency and error
Sample usage
- Anomaly detection
- Image recognition
- ADAS
|
|
aiint |
Artificial Intelligence Overview |
7 hours |
Kurs ten został stworzony dla menadżerów, architektów, analityków biznesowych i systemowych, menedżerów oprogramowania oraz wszystkich zainteresowanych przeglądem stosowania sztucznej inteligencji i prognozą dla jej rozwoju.
Artificial Intelligence History
Problem Solving
- Solving Problems by Searching
- Beyond Classical Search
- Adversarial Search
- Constraint Satisfaction Problems
Knowledge and Reasoning
- Logical Agents
- First-Order Logic
- Inference in First-Order Logic
- Classical Planning
- Planning and Acting in the Real World
- Knowledge Representation
Uncertain Knowledge and Reasoning
- Quantifying Uncertainty
- Probabilistic Reasoning
- Probabilistic Reasoning over Time
- Making Simple Decisions
- Making Complex Decisions
Learning
- Learning from Examples
- Knowledge in Learning
- Learning Probabilistic Models
- Reinforcement Learning
Communicating, Perceiving, and Acting;
- Natural Language Processing
- Natural Language for Communication
- Perception
- Robotics
Conclusions
- Philosophical Foundations
- AI: The Present and Future
|
|
Neuralnettf |
Neural Networks Fundamentals using TensorFlow as Example |
28 hours |
This course will give you knowledge in neural networks and generally in machine learning algorithm, deep learning (algorithms and applications).
This training is more focus on fundamentals, but will help you choosing the right technology : TensorFlow, Caffe, Teano, DeepDrive, Keras, etc. The examples are made in TensorFlow.
TensorFlow Basics
- Creation, Initializing, Saving, and Restoring TensorFlow variables
- Feeding, Reading and Preloading TensorFlow Data
- How to use TensorFlow infrastructure to train models at scale
- Visualizing and Evaluating models with TensorBoard
TensorFlow Mechanics
- Inputs and Placeholders
- Build the GraphS
- Train the Model
- The Graph
- The Session
- Train Loop
- Evaluate the Model
- Build the Eval Graph
- Eval Output
The Perceptron
- Activation functions
- The perceptron learning algorithm
- Binary classification with the perceptron
- Document classification with the perceptron
- Limitations of the perceptron
From the Perceptron to Support Vector Machines
- Kernels and the kernel trick
- Maximum margin classification and support vectors
Artificial Neural Networks
- Nonlinear decision boundaries
- Feedforward and feedback artificial neural networks
- Multilayer perceptrons
- Minimizing the cost function
- Forward propagation
- Back propagation
- Improving the way neural networks learn
Convolutional Neural Networks
- Goals
- Model Architecture
- Principles
- Code Organization
- Launching and Training the Model
- Evaluating a Model
|
Client Testimonials 
These courses are also available in other countries ››
