Channel Mixed3A mixed3a_255 mixed3a_254 mixed3a_253 mixed3a_252 mixed3a_251 mixed3a_250 mixed3a_249 mixed3a_248 mixed3a_247 mixed3a_246 mixed3a_245 mixed3a_244 mixed3a_243 mixed3a_242 mixed3a_241 mixed3a_240 mixed3a_239 mixed3a_238 mixed3a_237 mixed3a_236 mixed3a_235 mixed3a_234 mixed3a_233 mixed3a_232 mixed3a_231 mixed3a_230 mixed3a_229 mixed3a_228 mixed3a_227 mixed3a_226 mixed3a_225 mixed3a_224 mixed3a_223 mixed3a_222 mixed3a_221 mixed3a_220 mixed3a_219 mixed3a_218 mixed3a_217 mixed3a_216 mixed3a_215 mixed3a_214 mixed3a_213 mixed3a_212 mixed3a_211 mixed3a_210 mixed3a_209 mixed3a_208 mixed3a_207 mixed3a_206 mixed3a_205 mixed3a_204 mixed3a_203…… Continue reading InceptionV1 Feature Visualizations
Author: Akanksha NC
Bias Mitigation in Language Models by Steering Features
INTRODUCTION: What exactly is this bias, how does it manifest in Artificial intelligence (AI) models, and what steps can we take to eliminate it?Nearly 90% of all data was generated in the last decade, and internet usage, as well as the growth of social media, has influenced this data generation. For example, ChatGPT was trained…… Continue reading Bias Mitigation in Language Models by Steering Features
Superposition through Active Learning Lens
Here is the GitHub repo for this project: STALL Abstract Superposition or Neuron Polysemanticity are important concepts in the field of interpretability and one might say they are these most intricately beautiful blockers in our path of decoding the Machine Learning black-box.The idea behind this paper is to examine whether it is possible to decode…… Continue reading Superposition through Active Learning Lens
My most favorite place on Earth
Written and published in August 2013 So yes….By far ,among all the places I have visited on Earth, IUCAA is my most favourite place…I dont know,if it’s the architecture,the trees,the fact that Iucaa is related to astronomy about Iucaa that makes me fall in love with it over and over again….A person like me, who…… Continue reading My most favorite place on Earth
My Robocon Story
Written and published on 18 May 2011, so kindly forgive the lingo, apologies for the pain the lingo may cause, but keeping it original since it takes me back in time when I read it 😀 HI,I would like to share my ROBOCON story with you guys… the very first time when I saw robocon,it was on…… Continue reading My Robocon Story
Humans as Machines
Wondering how many humans have a high level of Obsessive Compulsive Disorder (OCD)? The kind where they are obsessed with order, maintenance, cleanliness, and doing things right (perceived notions of right anyway).Imagine how many humans regularly clean their toasters and their bathroom mirrors. How many people do regular maintenance on their cars and other machines?…… Continue reading Humans as Machines
Are Men and Women really Equal?
Written in October 2020 ‘reacting’ to the Hathras Gangrape case in India from September 2020, hence the raw language.
I plan to write about my thoughts on Gender Equality soon again, from a calmer mind state.
Time to have an AI BFF
We have come a long way from watching Jarvis give accurate answers to Ironman in science fiction movies to having LLMs be that Jarvis for anyone and everyone who needs one.
What’s in the name?
Every time, I think of these thoughts I am about to pen down, Shakespeare’s famous saying comes to my head, ‘What’s in the name?’Turns out Mr.Shakespear, it has quite a lot to do with a lot of things!I want to dwell a little about where I am coming from. I remember the first time when…… Continue reading What’s in the name?
Class Sensitivity in CIFAR-10
Understanding Class Sensitivity in Classification Problems using a CIFAR-10 Case Study.