Overview of Deep Learning
Deep learning states to a set of techniques by which we can achieve varying degrees of artificial intelligence by representing the working of a human brain
Deep learning is a subset of Machine Learning techniques that aim to achieve Artificial Intelligence. The unique feature of Deep Learning is its usage of various Artificial Neural Networks, that replicate the human brain
Just as in the brain, Artificial Neural Networks or ANNs also consist of neurons and synapses among them Deep Learning is one of the most highly desirable skills in AI
Post completion of this course participant will learn the foundations of Deep Learning, they will understand how to build neural networks, and also learn how to lead successful machine learning projects.
Duration
4 Days
Prerequisite for Deep Learning
A working knowledge of Python.
Course Outline for Deep Learning
Introduction
- What is deep learning?
- How it is different from Machine Learning?
- Deep Learning – Use cases
- Packages & Libraries available for implementing Deep learning
- Where does Deep Leaning fit into Data Science Ecosystem
- Quick Review of Machine Learning
Neural Networks with Tensor Flow
- How Deep Learning Works?
- Activation Functions
- Illustrate Perceptron
- Training a Perceptron
- Important Parameters of Perceptron
- What is TensorFlow?
- TensorFlow code-basics
- Graph Visualization
- Constants, Placeholders, Variables
- Creating a Model
- Step by Step – Use-Case Implementation
Neural Networks with Tensor Flow – Advanced
- Understand limitations of A Single Perceptron
- Understand Neural Networks in Detail
- Illustrate Multi-Layer Perceptron
- Backpropagation – Learning Algorithm
- Understand Backpropagation – Using Neural Network Example
- MLP Digit-Classifier using TensorFlow
- Tensor Board
- Summary
Python libraries for Data Science
- Installation & setup Python IDE – Anaconda
- NumPy
- SciPy
- Pandas,
- Matplotlib
- SciKit-Learn
- NLTK
Convolutional Neural Networks (CNN)
- Introduction to CNNs
- CNNs Application
- Architecture of a CNN
- Convolution and Pooling layers in a CNN
- Understanding and Visualizing a CNN
- Transfer Learning and Fine-tuning Convolutional Neural Networks
Recurrent Neural Network (RNN)
- Intro to RNN Model
- Application use cases of RNN
- Modelling sequences
- Training RNNs with Backpropagation
- Long Short-Term memory (LSTM)
- Recursive Neural Tensor Network Theory
- Recurrent Neural Network Model
- RBM and Autoencoders
- Restricted Boltzmann Machine
- Applications of RBM
- Collaborative Filtering with RBM
- Introduction to Autoencoders
- Autoencoders applications
- Understanding Autoencoders
Keras & Tflearn
- Define Keras
- How to compose Models in Keras
- Sequential Composition
- Functional Composition
- Predefined Neural Network Layers
- What is Batch Normalization
- Saving and Loading a model with Keras
- Customizing the Training Process
- Using TensorBoard with Keras
- Use-Case Implementation with Keras
- Define TFlearn
- Composing Models in TFlearn
- Sequential Composition
- Functional Composition
- Predefined Neural Network Layers
- What is Batch Normalization
- Saving and Loading a model with TFlearn
- Customizing the Training Process
- Using Tensor Board with TFlearn
- Use-Case Implementation with TFlearn
- Sample Capstone Projec
Cloud – Deep Learning with Amazon Web Service
- Deep Learning AMIs available
- Image Recognition API
- Common Practice to setup Deep Learning Project in cloud
