VJ AnandSequential Modeling for Reinforcement LearningThe idea of using transformers for different domains is gaining popularity. Academic literature reports experimentation or studies using…Jan 211Jan 211
VJ AnandEvidence Lower BoundEvidence Lower bound (ELBO) is a loss function that is used for variational inference. Networks that perform variational inference is also…Dec 4, 20231Dec 4, 20231
VJ AnandUnderstanding Entropy, KL-DivergenceDeriving KL-Divergence from first principles Let X be a random variable that can take one of the following n statesDec 4, 2023Dec 4, 2023
VJ AnandStochastic Gradient Langevine DynamicsThis paper introduced the concept of Bayesian Learning using Langevine Dynamics. In this short write up I will discuss some of the…Dec 2, 2023Dec 2, 2023
VJ AnandIn-Context Learning in Large Language ModelsWe all have been amazed how large language models (LLM) like GPT3/4/ChatGPT is able to perform tasks that it has never seen before, or…May 29, 2023May 29, 2023
VJ AnandSelf Supervised LearningOften times we encounter where we don’t have enough labeled data, what can we do in such cases. The area of self-supervised learning is…Aug 17, 2022Aug 17, 2022
VJ AnandRestricted Boltzmann MachineUnderstanding Restricted Boltzmann machine (RBM) architecture, its training and learning method is foundational to get better insight of…Jul 11, 2022Jul 11, 2022