Deep Learning In Python Training

Introduction

Keras Installation and API

• Installing Keras
• Getting started with Keras architecture
• An overview of predefined activation functions
• An overview of losses functions
• An overview of metrics
• An overview of optimizers
• Some useful operations
• Saving and loading the weights and the architecture of a model

Activation functions

• What are activation functions?
• sigmoid function
• hyperbolic Tangent function
• ReLu -Rectified Linear units
• softmax function

Tenserfow Basics

• What is Tensorflow ?
• Intallation of Tensorflow
• Placeholders in Tensorflow defining placeholders feeding placeholders with data
• Variables,Constant
• Computation graph
• visualize graph with Tensor Board
• MLP digit Classifier using Tensorflow

Feed-Forward Neural Networks with TensorFlow

• Feed-forward neural networks (FFNNs)
• Implementing Feed-forward neural networks (FFNNs)
• Implementing a multilayer perceptron (MLP)
• Tunning FFNNs hyperparameters

Tuning of Hyperparameters

• Regularization & Overfitting
• Regularizing a neural network with dropout
• Network Weight Initialization
• Vanishing gradients

Classifying Images with Convolutional Neural Networks

• Introduction to CNN
• Train a simple convolutional neural net
• Pooling layer in CNN
• Design a convolutional layer application
• Understanding and visualizing a CNN

Introduction to Recurrent Neural Networks(RNN)

• What are Recurrent Neural Networks (RNNs)?
• Understanding a Recurrent Neuron in Detail
• Long Short-Term Memory(LSTM)
• Back propagation Through Time(BPTT)
• Implementation of RNN in Keras
• Vanishing and Exploding Gradient Problem

Performing sentiment analysis of IMDb movie reviews

• using RNNs

Classifying Cats vs Dogs with a Convolutional Neural Network (CNN)