Introduction with Artificial Intelligence.
- What is AI (Artificial Intelligence) ?
- What types of intelligences we are talking about?
- Different definitions and Ultimate goal of AI.
- What are application areas for AI?
- History of AI and some real life examples of AI.
ML and other related terms to AI.
- What is ML and How it is related with AI?
- What is NLP and How it is related with AI?
- What is DL and How it is related with ML and AI?
- What are ANNs and DNNs and How are they related to AI?
A working example of AI and ML.
Project 1 – These simple tasks are to make you understand how AI and ML can find their applications in real life.
Python libraries for ML.
- What are Libraries, packages and Modules?
- What are top Python libraries for ML in Python?
Setting up Anaconda development environment.
- Why choosing Anaconda development environment?
- Setting up Anaconda development environment on Windows 10 PC.
- Verifying proper installation of Anaconda environment.
Getting into core development of ML.
- What is a classifier in ML?
- Important elements and flow of any ML projects.
- Let’s develop our first ML program – explanations
- Let’s develop our first ML program – development
Project – 2
These simple tasks are going to give you some great experience with Machine Learning introductory programs or better say, “Hello world” programs of Machine Learning.
Different ML techniques.
- What all ML techniques are there?
- Evaluation methods of all ML techniques.
(IRIS flower project) Developing complete project of ML.
- Developing complete ML project – understanding data set
- Developing complete ML project – understanding flow of project
- Developing complete ML project – visualizing data set through Python
- Developing complete ML project – development
- Developing complete ML project – concepts explanations
- –(Digit recognition project) Developing another project of ML.
- After completing these project, you have done and understood multiple complete projects of Machine Learning.
Introduction of Ai with Deep Learning
- CPU Software Requirements
- CPU Installation of PyTorch
- PyTorch with GPU on AWS
- PyTorch with GPU on Linux
- PyTorch with GPU on MacOSX
PyTorch Fundamentals: Matrices
- Matrix Basics
- Seed for Reproducibility
- Torch to NumPy Bridge
- NumPy to Torch Bridge
- GPU and CPU Toggling
- Basic Mathematical Tensor Operations
- Summary of Matrices
PyTorch Fundamentals: Variables and Gradients
- Summary of Variables and Gradients
Linear Regression with PyTorch
- Linear Regression Introduction
- Linear Regression in PyTorch
- Linear Regression From CPU to GPU in PyTorch
- Summary of Linear Regression
Logistic Regression with PyTorch
- Logistic Regression Introduction
- Linear Regression Problems
- Logistic Regression In-depth
- Logistic Regression with PyTorch
- Logistic Regression From CPU to GPU in PyTorch
- Summary of Logistic Regression
Feedforward Neural Network with PyTorch
- Logistic Regression Transition to Feedforward Neural Network
- Feedforward Neural Network in PyTorch
- More Feedforward Neural Network Models in PyTorch
- Feedforward Neural Network From CPU to GPU in PyTorch
- Summary of Feedforward Neural Network
Convolutional Neural Network (CNN) with PyTorch
- Feedforward Neural Network Transition to CNN
- One Convolutional Layer, Input Depth of 1
- One Convolutional Layer, Input Depth of 3
- One Convolutional Layer Summary
- Multiple Convolutional Layers Overview
- Pooling Layers
- Padding for Convolutional Layers
- Output Size Calculation
- CNN in PyTorch
- More CNN Models in PyTorch
- CNN Models Summary
- Expanding Model’s Capacity
- CNN From CPU to GPU in PyTorch
- Summary of CNN
Recurrent Neural Networks (RNN)
- Introduction to RNN
- RNN in PyTorch
- More RNN Models in PyTorch
- RNN From CPU to GPU in PyTorch
- Summary of RNN
Long Short-Term Memory Networks (LSTM)
- Introduction to LSTMs
- LSTM Equations
- LSTM in PyTorch
- More LSTM Models in PyTorch
- LSTM From CPU to GPU in PyTorch
- Summary of LSTM