PinnedAnkita SinhaP-tuning vs Prefix-tuning vs Prompt-tuning.With the advent of Large Language models which are trained to perform a variety of general tasks, there is a huge boost in finding ways to…Feb 19Feb 19
PinnedAnkita SinhaIntuition for Encoder-Based Models vs Decoder-Based ModelsWe will discuss the difference between Encoder-Based models and Decoder-based models and Everything in between.Feb 52Feb 52
PinnedAnkita SinhainNerd For TechIntroduction to FLOWERBuilding your own Federated Learning Platform using FLOWERMay 31, 2021May 31, 2021
PinnedAnkita SinhainTowards Data ScienceHierarchical Reinforcement LearningWith Options-Critic framework using tabular Q-LearningFeb 11, 20222Feb 11, 20222
Ankita SinhaUnlocking Text Similarity: Training Embeddings with Contrastive LearningEmbeddings are numerical representations of text, images, or other data. In the context of natural language processing, they capture…Sep 5Sep 5
Ankita SinhaYes, the options sampled from the policy over options can and should change during learning.Jan 311Jan 311
Ankita SinhainILLUMINATION’S MIRRORBeyoncé Said She Only Gives Herself One Day To Feel Sorry for HerselfAnd this advice changed my lifeJul 11, 2023Jul 11, 2023
Ankita SinhainNerd For TechThe Difference a World Model can make.To exploration in Reinforcement LearningJul 11, 2023Jul 11, 2023
Ankita SinhaSoft Q learningLet us start by understanding Q Learning and then extend it to Soft Q Learning.Apr 27, 20222Apr 27, 20222
Ankita SinhainILLUMINATION’S MIRRORA Father’s life lessons for his Daughter.lessons that helped a daughter break the stereotypes and make a her in this grey world.Mar 7, 20222Mar 7, 20222