From scratch implementation of the SAC algorithm in PyTorch for Lunar Lander.

From scratch implementation of the SAC algorithm in PyTorch for Inverted Pendulum.

A review of the mathematical essentials for recommender systems, comparing matrix factorization and graph neural networks.

In this post, we will explore the Low Rank Approximation (LoRA) technique for shrinking neural networks for embedded systems. We will focus on the Convolutional Neural Network (CNN) case and discuss the rank selection process.

In this article, we will discuss how values are passed between layers post quantization in PyTorch. We will also discuss why floating point operations are slower than integer operations.

A manual implementation of quantization in PyTorch.

In this post, we will explore the Low Rank Approximation (LoRA) technique for shrinking neural networks for embedded systems. We will focus on the Convolutional Neural Network (CNN) case and discuss the rank selection process.

An elementary explanation of the problem with full rank matrices in neural networks and their solution via low rank approximations. Detailed explanation on how to set up the optimization problem and how to solve it, in possibly linear time.