Deep Learning

This Deep Learning Training course will provide you with a basic understanding of the linear algebra, probabilities, and algorithms used in deep neural networks.

After learning the difference between deep learning and machine learning, delegates will gain in-depth knowledge of the different types of neural networks such as feedforward, convolutional, and recursive. At the end of this course, delegates will be able to build complex models that help machines to solve real-world problems.

Course Content:

• Introduction to Deep Learning
• Introduction to Deep Learning
• Define Deep Learning
• Neural Networks
• Deep Learning Applications
• Introduction to Deep Learning
• Necessity of Deep Learning over Machine Learning.
• History and evolution of various deep learning algorithms
• AI and how is Deep Learning one of the paths to AI in the recent era
• Types of Machine Learning and Deep Learning
• Why Deep Learning
• How to Train ANNs
• Introduction
• Perceptron Learning Rule
• Gradient Descent Rule
• Minimize Cost Function
• Tuning Learning Rate
• Stochastic vs Batch Gradient Descent
• Perceptron
• What is a Perceptron
• Logic Gates with Perceptron
• Activation Functions
• Sigmoid
• ReLU
• Softmax
• Hyperbolic Functions
• Multi-Layer ANN
• Intro to MLP
• Forward Propagation
• Minimize Cost Function
• Training Deep Neural Nets
• Vanishing/Exploding Gradients
• Xavier Initialization
• Leaky ReLUs and ELUs
• Batch Normalization
• Transfer Learning
• Naive Bayes
• Removing a Container
• Unsupervised Pre-Training
• Introduction to TensorFlow
• Intro to TensorFlow
• Computational Graph
• Key Highlights
• Creating a Graph
• Regression Example
• Gradient Descent
• Saving and Restoring Models
• layers API
• Keras-Based networks
• TensorBoard
• Convolutional Neural Networks
• Intro to CNNs
• Convolution Operation
• Kernel Filter
• Feature Maps
• Pooling
• CNN Architecture
• Implement CNN in Tensor Flow
• Recurrent Neural Networks
• Intro to RNNs
• Unfolded RNNs
• Basic RNN Cell
• Dynamic RNN
• Training RNNs
• Time-series predictions
• LSTM
• Word Embedding’s
• Seq2Seq Models
• Implement RNN in TensorFlow
• Keras 
• Introduction of Keras
• Understanding of Keras Model Building Blocks
• Illustration of different Compositional Layers
• Process based use cases’ implementations
• TFlearn 
• Introduction of TFlearn
• Understanding of TFlearn Model Building Blocks
• Illustration of different Compositional Layers
• Step-wise use-cases implementations