Hardware and Software Requirements

• A laptop running 64 bit OS (Linux/OSX/Windows)
• Internet connection and a google

  Pre-requisites

• A basic understanding of programming concepts
• Programming knowledge of python is a plus

Day 1:

Introduction to Deep Learning (Date: 5.2.2019: 9:30 - 11:00 a.m.)

• Deep learning in the context of Machine Learning and Artificial Intelligence
• Applications of Deep Learning
• What is a neural network?
• Why Deep Learning?

Dive deep into Deep Learning (Date: 5.2.2019: 11:30 a.m. - 1:00 p.m.)

• Jupyter notebook using Google Colab
• Train a deep network using TensorFlow/Keras
• How to choose between deep neural networks?
• Effectively regularize a simple deep network.
• Train a competitive deep network via model exploration and hyper-parameter tuning.

Convolutional Neural Networks (Date: 5.2.2019: 2:00 p.m. - 4:00 p.m.)

• Train a simple convolutional neural net.
• Explore the design space for convolutional nets.
• Transfer Learning
• Overview of different architectures – VGG; AlexNet etc.

Day 2:

Recurrent Neural Networks (Date: 6.2.2019: 9:30 - 11:00 a.m.)

• Back Propogation through time
• Vanishing Gradient Problem
• Long Short term memory (LSTM) and Gated Recurrent Unit (GRU)
• Character Prediction using Keras

Auto-encoders (Date: 6.2.2019: 11:30 a.m. - 1:00 p.m.)

• Single layer auto-encoders
• Stacked Auto-encoders
• Dimension Reduction
• Anomaly Detection

Deep Natural Language Processing (Date: 6.2.2019: 2:00 p.m. - 4:00 p.m.)

• Embedding Concept in the context of Natural Language Processing
• Natural Language Understanding pipeline
• Word Embedding
• Word Vector Representations: Glove
• Word Vector Representations: word2vec
• Word Vector Representations: OpenAI Transformer, ELMo, BERT
• Text Classification using Word Embedding, CNN and RNN

Day 3:

Model Debugging and deployment (Date: 7.2.2019: 9:30 - 11:00 a.m.)

• TensorFlow Debugger
• Tensorboard
• Deploying models in real world

Introduction to Reinforcement Learning (Date: 7.2.2019: 11:30 a.m. - 1:00 p.m.)

• Limitations of Supervised and Unsupervised learning
• Markov Descisions Processes
• Grid world
  • Policy Iteration
  • Value Iteration
  • Monte Carlo Policy Evaluations
  • Temporal Differencing, SARA, Q-Learning
• Introduction to Deep Reinforcement Learning

Venue:
School Of I.C.T,
Gautam Buddha University
Yamuna Expressway,
Greater Noida
Gautam Budh Nagar
Uttar Pradesh (India) - 201308
Phone No.: 0120-2344200