Posts

Notes on Multi Class Explainable Unlearning for Image Classification via Weight Filtering

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper Multi Class Explainable Unlearning for Image Classification via Weight Filtering by Samuele Poppi, Sara Sarto, Marcella Cornia, Lorenzo Baraldi and Rita Cucchiara. Samuele P., et. al....

Notes on Denoising Diffusion Probabilistic Models

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a summary of the paper Denoising Diffusion Probabilistic Models by Jonathan Ho, Ajay Jain and Pieter Abbeel, from University of California, Berkeley. The paper was published in 2020 and is a follow up on Diffusion Probabilistic Models (DPM)....

Notes on Deep Unsupervised Learning Using Nonequilibrium Thermodynamics

Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a summary of the paper Deep Unsupervised Learning using Nonequilibrium Thermodynamics by Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan and Surya Ganguli, from Stanford University and University of California, Berkeley. The paper was published in 2015 and it is the first one to introduce the concept of Diffusion Probabilistic Models (DPMs) or, in short, Diffusion Models....

Attention and Context based Embeddings

Attention mechanisms are a type of techniques used in natural language processing (NLP) tasks that allow a model to focus on specific parts of the input when processing a sequence, rather than considering the entire sequence at once. These methods can improve the performance of the model by allowing it to efficiently process long sequences of text and make more accurate predictions. To some extend, attention mechanisms are motivated by how human visual attention focuses on different regions of an image or how correlates words in a sentence....