Second AI Winter School

This repository comprises of all the lectures slides, keynotes slides, ipython notebooks used during "Second AI Winter School" organized by the NAAMII at Pokhara, Nepal from December 10, 2019 to December 20, 2019.

Major topics that are covered in this Winter School are as follows:

• AI and Machine Learning, Bayesian Machine Learning, Natural Language Processing by Prof. Suresh Manandhar from University of York.

• Artificial Curiosity by Prof. Karl Friston from University College London.

• Geometric Deep Learning by Prof. Michael Bronstein from Imperial College London.

• Deep Learning, Variational Auto Encoder and Generative Adversarial Network by Danda Pani Paudel.

• Convolutional Neural Networks and 3D Vision by Ajad Chatkuli.

• Probability, Statistics and Graphical Models by Samrachana Adhikari from NYU.

• Object Detection and Uncertainity by Sreyasha.

• Computational Neuroscience - Convolution in the brain by Chris Pack.

• Computational Neuroscience - Primate visual systems: Learning to see without a teacher by Ehud Zohary.

• Reinforcement Learning by Florian Golem.

• Quantum Machine Learning by Chahan Kropf.

• Robotic Vision (SLAM) by Suman.

• AI and Ethics by Juliane klatt

• AI and Society by Dovan Rai.

• Medical Informatics by Bishesh, Taman, Sharib

• Bioinformatics by Maria

---

Note : * Please feel free to fork and update the contents. I will be very happy to receive updates and upgrades.

---

Outline

Day 1

AI and Society

1. AI and Society Slide

2. Group Assignments

3. Group Discussion Questions

Python, Numpy and Pandas Basics

Python Introduction Notebooks

1. Hello World
2. Data Types and Basic Operations
3. Lists and Dictionary
4. File Handling

Numpy Introduction Notebooks

1. Arrays
2. Matrix

Pandas Introduction Notebook

1. Pandas Basics

Regressions

1. Linear Regression Notebook

2. Logistic Regression Notebook

Image Stitching using OpenCV

1. Lecture Slide

2. Image stitching Notebook

Day 2

Introduction to AI and Machine Learning

Artificial Curiosity by Karl Friston

Image Representation

1. Face Recognition Modern Vs Conventional

2. Face Recognition using Eigen Faces

Lab

1. Face Recognition Lab note

2. Face Recognition steps notes

3. Face Recognition Lab Notebook

4. Autoencoders with MNIST dataset Notebook

5. Denoising with Autoencoders Notebook

Day 3

Geometric Deep Learning by Michael Bronstein

SIAM by Michael Bronstein

Deep Learning

1. Fundamentals

2. Optimization

Lab

1. Neural Network Basics

Day 4

Convolutional Neural Network

Probability

1. Probability Lecture slide

2. Probability Cheat Sheet

3. Problem set 1

4. Problem set 2

Lab

1. Instructions for Lab of CNN

2. Lab sample exercise for CNN

3. Lab Notebook for CNN exercise

Day 5

Bayesian Machine Learning

Object Detection and Uncertainity

Computational Neuro Science - Convolution in Brain

Lab on Neuro Science

1. Lab Instruction Doc

2. Lab Instruction Code

3. Lab in Notebook

Day 6

AI in Education

Causality of AI in Education

Graphical Models

1. Hierarchial Models

2. Graphical Models

Reinforcement Learning by Florian Golem

1. Lecture slide by Florian Golem with animation

2. Lecture slide by Florian Golem without animation

Lab

1. Reinforcement Learning Lab on Pendulum

Day 7

Day 8

NLP Introduction by Ashutosh Modi

Day 9

3D Vision by Ajad Chatkuli

Day 10

VAE and GAN by Danda Pani Poudel

SLAM by Suman Raj Bista

Quantum Machine Learning by Chanan Kropf