Arani Consulting

Email:info@araniconsulting.com

Module 1

Unit 1: Deep Learning Introduction

1. Introduction to DL problems
2. DL terminologies
3. DL project workflow
4. DL real life examples

Unit 2: Jupyter Notebook introduction

1. Working with Jupyter notebooks
2. Markdown and Code blocks
3. Keyboard shortcuts

Unit 3: Python Basics

1. Python syntax
2. Basic data types
3. Basic data structures

Unit 4: Python advanced

1. Numpy Arrays
2. Plotting using Matplotlib
3. Pandas Dataframes
4. Introduction to Keras

Module 2

Unit 1: Artificial Neural Networks (ANN)

1. What is a Neuron
2. What are Activation Functions
3. How does a neural network learn?
4. Gradient Descent
5. Stochastic Gradient Descent
6. Back Propagation
7. Artificial Neural Networks in Keras
8. Linear model (No Hidden Layers)
9. Neural network with a single hidden layer

Module 3

Unit 1: Convolutional Neural Networks (CNN)

1. Image representation
2. ConvNets or CNN
3. Convolution Layer
4. Padding
5. How do we learn these kernels?
6. Can we force a particular kernel to learn to recognize a specific feature?
7. Non-Linear Activations
8. Downsampling or Pooling
9. Full Connection
10. Loading MNIST data
11. Implementation of CNN in Keras

Module 4

Unit 1: Auto Encoders (AE)

1. Introduction to Auto Encoders
2. Why learn identity function?
3. Properties of learned function
4. Real world applications of Autoencoders
5. MNIST Dimensionality Reduction
6. A Simple Autoencoder
7. Functional API
8. Deep Autoencoder
9. Convolutional Autoencoder
10. Image Denoising
11. Data Specific Encoding and Decoding

Module 5

Unit 1: Recurrent Neural Networks (RNN)

1. Introduction to Recurrent Neural Networks
2. Sequence Learning
3. Regular Neural Network
4. Simple RNN
5. Problems with RNN
6. Long Short Term Memory (LSTM)
7. Stacked (Deep) LSTM Model
8. Deep Stacked LSTM with Stateful Cells
9. Gated Recurrent Unit