Medium

nachiket tanksale

nachiket tanksale

·

23h ago

Day 8: ML Infrastructure, Training at Scale, Data Parallelism, and Distributed Training

Read the Day 7 story here.

nachiket tanksale

·

4d ago

Day 7: RAG Systems, Retrieval Is an ML Problem, Not Just a Vector Database

Read Day 6 here

nachiket tanksale

·

Nov 3

Day 6: Attention and Transformers: Why Self-Attention Works

Read Day 5 here.

nachiket tanksale

·

Nov 1

Day 5: ML System Design, Designing a Production Recommendation System

Read Day 4 here

nachiket tanksale

·

Oct 30

Day 4: Neural Network Backpropagation: What Is Actually Being Differentiated?

Read Day 3 here

nachiket tanksale

·

Oct 29

Day 3: Maximum Likelihood, MAP, and the Bayesian View of Regularization

Read Day 2 here

nachiket tanksale

·

Oct 24

Day 2: Bias–Variance, Regularization, and Generalization

Read Day 1 Problem here.

nachiket tanksale

·

Oct 21

Day 1: Logistic Regression, the Model Underneath a Surprising Amount of ML

About this series

nachiket tanksale

·

Jun 19, 2025

Illusion-ception — Illusion of illusion of illusion of illusion of Thinking

Note: This article is just for fun and does not have any technical or profound discussion, just take it with a pinch of salt. (Just as you…

Illusion-ception — Illusion of illusion of illusion of illusion of Thinking

In

Becoming Human: Artificial Intelligence Magazine

by

nachiket tanksale

·

Nov 3, 2020

Vision Transformers — attention for vision task.

Recently there’s paper “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale” on open-review. It uses pretrained…

Vision Transformers — attention for vision task.

nachiket tanksale

nachiket tanksale

Programmer, Working on NLP , www.linkedin.com/in/nachikettanksale, https://github.com/nachiket273, https://twitter.com/nachiket273

Following

Help

Status

About

Careers

Press

Blog

Store

Privacy

Rules

Terms

Text to speech