EncartaLabs

PyTorch

Deep Learning with PyTorch training course will teach you how to develop deep learning models using Pytorch. The course will start with Pytorch's tensors and Automatic differentiation package. Then each section will cover different models starting off with fundamentals such as Linear Regression, and logistic/softmax regression. Followed by Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers. Then Convolutional Neural Networks and Transfer learning will be covered.

PyTorch - Predictive Modeling training course will teach you how to use Pytorch for developing machine learning model for regression and classificaton. It willl also teach how to visualize the data and model using Tensorboard.

Sequential Data is the more prevalent data form such as text, speech, music, DNA sequence, video, drawing. Analysing sequential data is one of the key goals of machine learning such as document classification, time series forecasting, sentimental analysis, language translation. Seq2seq models have been used to process sequenital data. Seq2seq model has transformed the state of the art in neural machine translation, and more recently in speech synthesis. In PyTorch - Sequential Data Modeling training course, we will teach Seq2seq modeling with Pytorch.

Generative Models are gaining a lot of popularity recently among data scientists, mainly because they facilitate the building of AI systems that consume raw data from a source and automatically builds an understanding of it. Unlike supervised learning methods, generative models do not require labelled data. Pytorch is one of the most versatile Deep Learning to implement generative models. In PyTorch - Generative Models training course, you will learn how to use Pytorch for generative models.

Deep Reinforcement learning is a type of machine learning that allows machines and software agents to act smart and automatically detect the ideal behavior within a specific environment, in order to maximize its performance and productivity. Reinforcement Learning is becoming popular because it not only serves as an way to study how machine and software agents learn to act, it is also been used as a tool for constructing autonomous systems that improve themselves with experience. Pytorch is one of the most versatile Deep Learning to implement deep reinforcement learning. In PyTorch - Deep Reinforcement training course, you will learn how to use Pytorch for reinforcement learning.

By attending Deep Learning with PyTorch workshop, delegates will learn:

  • Installing Pytorch
  • Math Operations with Pytorch
  • Neural Networks with Pytorch
  • Deep Learning with Pytorch
  • Image Recognition with Convolutional Neural Network (CNN)
  • Sequential Data Processing Recurrent Neural Network (RNN)

By attending PyTorch - Predictive Modeling workshop, delegates will learn to:

  • Understand machine learning principles to assess business insights
  • Aggregate data to help test problem using Pytorch
  • Apply predictive data modeling techniques to identify underlying trend and find relevant insights from the data
  • Develop prototype classification model using machine learning techniques to gain new insight from data.
  • Identify patterns using convolutional neural network model to derive insights and make decision
  • Use Tensorboard data visualisation tool to create interactive visualizations of data

By attending PyTorch - Sequential Data Modeling workshop, delegates will learn to:

  • Recap of RNN and LSTM
  • 1D Convolution
  • Sequence 2 Sequence Model in Pytorch
  • Attention Mechanism
  • Neutral Machine Translation

By attending PyTorch - Generative Models workshop, delegates will learn:

  • Neural Transfer Using Pytorch
  • DCGAN
  • Style Transfer with GAN

By attending PyTorch - Deep Reinforcement workshop, delegates will learn to:

  • Understand the fundamental concepts of Q Values and Q Tables
  • Code Q Learning and SARSA
  • Use OpenAI Gym
  • Code Deep Q Network
  • Code Policy Gradient

For Deep Learning with PyTorch: Knowledge of
  • Basic Python
For PyTorch - Predictive Modeling: Knowledge of
  • Basic Pytorch
  • Basic Machine Learning
For PyTorch - Sequential Data Modeling: Knowledge of
  • Basic Python
  • Basic Pytorch
  • Basic Machine Learning
For PyTorch - Generative Models: Knowledge of
  • Python
  • Pytorch
  • Machine Learning
For PyTorch - Deep Reinforcement: Knowledge of
  • Basic Python
For Deep Learning with PyTorch && PyTorch - Predictive Modeling && PyTorch - Sequential Data Modeling courses
  • Data Scientists
  • Data Analysts
  • Engineers
For - Generative Models && PyTorch - Deep Reinforcement courses
  • AI Developers
  • Artificial Intelligence Engineers
  • Data Scientists

COURSE AGENDA

Deep Learning with PyTorch
(Duration : 2 Days)

1

Overview of Deep Learning and Pytorch

  • Overview of Deep Learning
  • Introduction to Pytorch
  • Install and Run Pytorch
2

Basic Pytorch Operations

  • Pytorch Tensors
  • Basic Pytorch Tensor Operations
  • Compute Gradients with Autograd
3

Datasets

  • MNIST Handwritten Digits and Fashion Datasets
  • CIFAR Image Dataset
4

Neural Network for Regression

  • Introduction to Neural Network (NN)
  • Activation Function
  • Loss Function and Optimizer
  • Machine Learning Methodology
  • Build a NN Predictive Regression Model
  • Load and Save Model
5

Neural Network for Classification

  • Softmax
  • Cross Entropy Loss Function
  • Build a NN Classification Model
6

Convolutional Neural Network (CNN)

  • Introduction to Convolutional Neural Network (CNN)
  • Convolution & Pooling
  • Build a CNN Model for Image Recognition
7

Recurrent Neural Network (RNN)

  • What is RNN?
  • RNN Architecture
  • Long Term Dependencies
  • LSTM and GRU
8

Transfer Learning

  • Introduction to Transfer Learning
  • Pre-trained Models
  • Transfer Learning for Feature Extraction & Fine Tuning
PyTorch - Predictive Modeling
(Duration : 2 Days)

1

Overview of Deep Learning and Pytorch

  • Overview of Deep Learning
  • Introduction to Pytorch
  • Install and Run Pytorch
  • Basic Pytorch Tensor Operations
  • Computation Graphs
  • Compute Gradients with Autograd
2

Neural Network for Regression

  • Introduction to Neural Network (NN)
  • Activation Function
  • Loss Function and Optimizer
  • Machine Learning Methodology
  • Build a NN Predictive Regression Model
  • Load and Save Model
3

Neural Network for Classification

  • Softmax
  • Cross Entropy Loss Function
  • Build a NN Classification Model
4

Convolutional Neural Network for Pattern Recognition

  • Introduction to Convolutional Neural Network (CNN)
  • Convolution & Pooling
  • Build a CNN Model for Pattern Recognition
5

Data Visualization with Tensorboard

  • Set up TensorBoard
  • Inspect a model architecture using TensorBoard
  • Create interactive Visualizations
PyTorch - Sequential Data Modeling
(Duration : 1 Day)

1

Word Embedding

  • One Hot Encoding of Words
  • Word Embedding
  • Using Pre-Training Word Embedding
2

Review on RNN and LSTM

  • Recurrent Neural Network (RNN)
  • Long Short Term Memory (LSTM) and GRU
  • Stacked RNN
  • Bidirectional RNN
3

1D Convolution

  • 1D Convolution on Sequential Data
  • Combiniing 1D Convolution and RNN for long sequence
4

Sequence To Sequence Model in Pytorch

  • What is Seq2Seq Model
  • Encoder and Decoder
  • Seq2Seq
5

Neural Machine Translation (Optional)

  • Attention Mechanism
  • Neural Machine Translation with Seq2Seq and Attention
PyTorch - Generative Models
(Duration : 1 Day)

1

Overview of Generative Models

  • What is Generative Models
  • Application of Generative Models
  • Types of Generative Models
  • Online Generative Model Demo with Sketch-RNN
  • Installing Google Colab
2

DeepDream

  • Recap on Convolutional Neural Networks (CNN)
  • Recap on Transfer Learning
  • What is DeepDream?
  • DeepDream Applications
  • DeepDream Implementation
3

Neural Style Transfer

  • What is Neural Style Transfer?
  • Neural Style Transfer Applications
  • Neural Style Transfer Implementation
4

Variational Autoencoder (VAE)

  • What is Autoencoder
  • Variational Autoencoder (VAE)
  • VAE Implementation
5

Generative Adversarial Networks (GAN)

  • What is GAN?
  • GAN Applications
  • Basic DCGAN Architecture
  • DCGAN Implementation
  • GAN Challenges and Tricks
6

Text Generation (Optional)

  • Recap on Recurrent Neural Networks (RNN)
  • Recap on Long Short Term Memory (LSTM)
  • Char by Char Text Generation with LSTM
PyTorch - Deep Reinforcement
(Duration : 1 Day)

1

Introduction to Reinforcement Learning

  • What is Reinforcement Learning (RL)
  • Applications of RL
  • Basic Concepts of RL
  • RL Methods
  • Key RL Algorithms
2

Q Learning

  • Q Value and Q-Table
  • Q-Learning and Bellman Equation
  • Q-Learning Algorithm
  • Epsilon Greedy Explore-Exploit Strategy
  • Implementation of Q-Learning in Python
  • Max Q-Value Policy
3

SARSA

  • On-Policy vs Off-Policy Learning
  • What is SARSA?
  • SARSA Value Update
  • Sarsa Algorithm
  • Implementation of SARSA in Python
4

OpenAI Gym

  • What is OpenAI Gym
  • Install OpenAI Gym
  • OpenAI Gym Operations
  • Q-Learning on OpenAI Gym
  • SARSA on OpenAI Gym
5

Deep Q-Network (DQN)

  • Why Deep Q-Learning?
  • Challenges of Implementing Deep Q-Learning
  • Target Network & Experience Replay
  • What is Deep Q Network (DQN)?
  • DQN Algorithm
  • Implementing DQN on OpenAI Gym with Keras
6

Policy Gradient

  • Limitation of DQN
  • Policy Based Methods
  • Policy Gradient Theorem
  • REINFORCE Algorithm
  • Implementing PG on OpenAI Gym with Keras

Encarta Labs Advantage

  • One Stop Corporate Training Solution Providers for over 4,000 Modules on a variety of subjects
  • All courses are delivered by Industry Veterans
  • Get jumpstarted from newbie to production ready in a matter of few days
  • Trained more than 50,000 Corporate executives across the Globe
  • All our trainings are conducted in workshop mode with more focus on hands-on sessions

View our other course offerings by visiting http://encartalabs.com/course-catalogue-all.php

Contact us for delivering this course as a public/open-house workshop/online training for a group of 10+ candidates.

Top