Deep Learning Artificial Intelligence with PYTHON

 

Course Content (Duration 5 Days – Deep Learning Data Science with Python)

Lesson

Topic

Introduction to Linear Algebra and to Mathematics for Machine Learning Introduction: Mathematics & Machine Learning
Linear Algebra
Introduction to Vectors
Operations with Vectors
Exercise
Modulus & Inner Products
Cosine & Dot Products
Projection
Changing the Basis
Basis, Vector Space & Linear Independence
Application
Assessment
Matrices, vectors, and solving simultaneous equation problems
How matrices transform space
Types of matrix transformation
Determinants and inverses
Eigenvalues & Eigenvectors
Multivariate Calculus What is Calculus?
Multivariate Calculus
Optimization
Gradient Descent
Regression
Exercise
AI and Deep learning introduction What is AI and Deep learning
Brief History of AI
Deep learning: Over the years
Demo & discussion: Self-driving car
Applications of Deep learning
Challenges of Deep learning
Building ML & AI Projects Workflow of a machine learning project
Workflow of a data science project
How to choose an ML/AI project
Case study: Object Detection using YOLO
Business Examples
JPMorgan Chase and their COiN
Wells Fargo: AI-Powered ChatBot
Bank of America: Erica
HDFC Bank: EVA
Artificial Neural Network Biological Neuron Vs Perceptron
Shallow neural network
Training a Perceptron
Demo: classification
Backpropagation
Role of Activation functions & backpropagation
Different Activation functions
Backprop Illustration
Optimization
Regularization
Demo
Deep Neural Network & Tools Deep Neural Network: why and applications
Designing a Deep neural network
Working of a feed-forward network
Forward and Backward Propagation
Loss Function
Choosing the right Loss Function
Hyperparameter Tuning
Building your deep neural network: Step by Step
Deep Learning Tools: Pytorch, Caffe
Demo
Exercise
Convolutional Neural Net Introduction to Computer Vision: Image Analysis
Edge Detection
CNN
CNN Architecture
Demo
Deep CNN
Object Detection
Object Detection using Yolo
CNN Visualization
Demo & Exercise
Deep Neural Net optimization & Regularization Optimization algorithms
SGD, Momentum, NAG, Adagrad, Adadelta, RMSprop, Adam
Demo
Batch normalization
Demo
Exploding and vanishing gradients
Hyperparameter tuning
Visualizing a Deep Neural Net
Demo
Recurrent Neural Networks Need for a Neural Network dealing with Sequences
What are Recurrent Neural Networks (RNNs)?
Understanding a Recurrent Neuron in Detail
LSTM
LSTM Demo
Gated Recurrent Units (GRUs)
LSTM vs GRUs
Vanishing and Exploding Gradient Problem
Exercise
Reinforcement Learning Formulating a reinforcement learning problem
Comparison with other machine learning methodologies
Framework for solving Reinforcement learning problems
An implementation of Reinforcement Learning
Increasing the complexity
Peek into recent RL advancements
Demo
Exercise
Twin Neural Networks: The adversarial and collaborative approaches Power of twin networks
Adversarial training of twin Network: GAN
Demo
Conditional GAN
Demo
Image Transformation example applications( Style and cycle)
Demo code and Lesson End exercise ( Young to old kaggle dataset)
Exercise
AutoEncoders Collaborative twin networks
Autoencoder for anamoly detection
Demo
variational and generational AutoE
Demo
AutoEncoder as denoising solution
Demo
Project Course End Project