Posts by Category

Understanding how increasing the number of layers increases the training error after a point and how Resnets solve it

less than 1 minute read

Published: March 10, 2019

Read Omkar Ranadive's answer to Why its that with increasing layers of neural network after a point increases the training error (ResNets)? on Quora Read more

Do neural nets generalize better with larger data sets?

less than 1 minute read

Published: November 20, 2018

Read Omkar Ranadive's answer to Does neural network generalize better if it is trained on a larger training data set? Are there any scientific papers showing it? on Quora Read more

Overcoming local minima problem in neural networks

less than 1 minute read

Published: October 05, 2018

Read Omkar Ranadive's answer to How do I overcome a local minimum problem in neural networks? on Quora Read more

Why do activation functions need to be non-linear?

less than 1 minute read

Published: July 05, 2018

Read Omkar Ranadive's answer to Why do we need non-linear activation functions in a neural network? on Quora Read more

What to do in case similiar inputs are labeled with different outputs?

less than 1 minute read

Published: June 25, 2018

Read Omkar Ranadive's answer to In classification, is it okay to have (in the training set) similar inputs that are labeled with different outputs? If not, how do I deal with that? on Quora Read more

Lecture 10 - Applying RL to Games [Notes]

9 minute read

Published: May 05, 2020

• Title: Appling RL to Games
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 7
• Lecture Slides: Slides

Lecture 9 - Advanced Exploration [Notes]

13 minute read

Published: May 04, 2020

• Title: Advanced Exploration
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 9
• Lecture Slides: Slides

Lecture 8 - Integrating Learning and Planning [Notes]

10 minute read

Published: May 03, 2020

• Title: Integrating Learning and Planning
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 8
• Lecture Slides: Slides

Lecture 7 - Policy Gradients [Notes]

9 minute read

Published: May 02, 2020

• Title: Policy Gradients
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 7
• Lecture Slides: Slides

Lecture 6 - Value Function Approximation [Notes]

8 minute read

Published: May 01, 2020

• Title: Value function approximation
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 6
• Lecture Slides: Slides

Lecture 5 - Optimizing Model Free Techniques (Model Free Control) [Notes]

11 minute read

Published: March 10, 2020

• Title: Optimizing Model Free Techniques
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 5
• Lecture Slides: Slides

Lecture 4 - Model Free Techniques - MC and TD[Notes]

11 minute read

Published: March 10, 2020

• Title: Model Free Techniques - Monte Carlo and Temporal Difference
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 4
• Lecture Slides: Slides

Lecture 3 - Dynamic Programming in RL [Notes]

11 minute read

Published: March 09, 2020

• Title: Markov Processes
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 3
• Lecture Slides: Slides

Lecture 2 - Markov Processes [Notes]

9 minute read

Published: March 06, 2020

• Title: Markov Processes
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 2
• Lecture Slides: Slides

Lecture 1 - Introduction to Reinforcement Learning [Notes]

6 minute read

Published: March 02, 2020

• Title: Introduction to Reinforcement Learning
• Description: The lecture notes are based on David Silver’s lecture video.
• Video link: RL Course by David Silver - Lecture 1
• Lecture Slides: Slides

Relation between Dynamic Programming and Reinforcement Learning

less than 1 minute read

Published: March 23, 2019

Read Omkar Ranadive's answer to How is dynamic programming related to a reinforcement learning algorithm? on Quora Read more

Maximum Likelihood, Fisher Information, Cramer Rao Inequality

3 minute read

Published: September 09, 2020

Importance Sampling

4 minute read

Published: April 27, 2020

• Importance Sampling: Intro
• Importance Sampling: Intuition
• Importance Sampling: Normalizing constants

Variational Lower Bounds (ELBO)

1 minute read

Published: April 20, 2020

Original Video link:

• Variational Lower Bounds