shashank JainDiscovering the Inner Workings of Language Models: A Deep Dive into “The Remarkable Robustness of…Introduction:Jul 13Jul 13
shashank JainUnderstanding Entropy-SGD: A Way to Train Better AI ModelsToday I try to cover a very interesting paper https://arxiv.org/abs/1611.01838 . The paper talks about usign Entropy within SGD to…Jul 11Jul 11
shashank JaininGoPenAIOptimizing LSTM Autoencoder Latent Dimension using Mutual Information and BOIntroduction:Jul 10Jul 10
shashank JaininGoPenAIResidual Networks Explained: Deep Learning with Residual NetworksIntroductionJun 29Jun 29
shashank JaininGoPenAIUnderstanding Kolmogorov-Arnold Networks (KANs) and Their Application in Variational AutoencodersToday, we’ll be diving into the Kolmogorov-Arnold Networks, or KANs for short. We’re going to explore how KANs can potentially…Jun 28Jun 28
shashank JainUnderstanding Cambrian-1: A Deep Dive into Advanced Visual-Language AIIntroduction:Jun 26Jun 26
shashank JainUnlocking the Power of LoRA: Efficient Fine-Tuning with Low-Rank AdaptationImagine having a pre-trained model that’s great at identifying different breeds of dogs. It’s been trained on a vast dataset, capturing…Jun 15Jun 15
shashank JainAutoEncoders and Variational AutoEncoders: An IntroductionIn this blog, I will try to formulate AE and VAE from a probablistic framework point of view and explain how they work and what are the…Jun 9Jun 9
shashank JainExploring Java Virtual ThreadsVirtual threads are a new feature in Java that aims to dramatically reduce the effort of writing, maintaining, and observing…Feb 25Feb 25