A learning from a mistake is a learning iff it's not repeated.
- a wise person
[Read More]
Knowledge transfer in Reinforcement Learning
....can RL be a little easier?
Generally, I come to the conclusions or my learnings from any project at the end of these blog posts but this time, I am tempted (only 50% upset about it) to begin the post by that and here it goes: classic RL alone has a very little chance of being...
[Read More]
Semantic Segmentation
....when weights and uncertainities are good
Machine learning models follow garbage in, garbage out policy: the quality of the model’s output is determined by what you feed to it. The final objective of most of the ML models is to find out the underlying data generating distribution and the performance of your model depends on a...
[Read More]
Collaborative filtering using Autoencoders
....similar to the items you viewed :p
This post is a little late than earlier ones. The semester has started and between all the classes and HWs, I get less time to focus on the projects I want to do. Other than that I had a lot of interviews for summer internship in the past month but...
[Read More]
Financial time series forecast
....or effectiveness of attention based models
Stock market prediction is usually considered as one of the most challenging issues among time series predictions due to its noise and volatile features. People have come up with many techniques to deal with the noise part, one of the most common approaches being decomposing the signal using Fourier Transform...
[Read More]