Skip to content
View khetansarvesh's full-sized avatar
💭
I may be slow to respond.
💭
I may be slow to respond.
4 followers · 3 following
  • Mumbai

Block or report khetansarvesh

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
khetansarvesh/README.md

Coding

A passionate Deep Learning / Mathematics enthusiast

I have written this comprehensive guide that takes you from the basics of Machine Learning to becoming an expert in Deep Learning. This book bridges theoretical foundations with cutting-edge applications, giving you both the knowledge and practical skills needed in today's AI landscape. Note: I continuously update this book as new technologies like LLMs emerge and as my own understanding deepens.

This book is designed for computer science students, software engineers, data scientists, and mathematics enthusiasts who want to build a solid foundation in deep learning. Whether you're starting with basic programming knowledge or transitioning from traditional machine learning, you'll find a structured path forward.

Prerequisites

  • Linear Algebra - Understanding vectors, matrices, eigenvalues
  • Probability - Basic concepts of random variables, distributions, and Bayesian thinking
  • Calculus - Derivatives, gradients, chain rule, and optimization fundamentals
  • Python Programming - Comfortable with NumPy, pandas, and basic syntax

Part 1 : Uni-Modal (Single Modality) Data Modelling :

Part 2 : Multi-Modal Data Modelling

Coding

khetansarvesh

⚒️ Languages and Tools ⚒️:

aws azure c cassandra cplusplus docker gcp git graphql hadoop hive jenkins kafka kubernetes mongodb mysql opencv pandas postgresql python pytorch redis scikit_learn seaborn tensorflow

Latest from my TechBlogs

khetansarvesh

 khetansarvesh

khetansarvesh

Pinned Loading

  1. NLP Public

    Implemented projects from noncontextual word embeddings like Word2Vec to contextual word embeddings like ELMO, GPT, BERT to solving NLP tasks Sentence Level Classification (sentimental analysis & T…

    Jupyter Notebook

  2. CV Public

    Implementation of algorithms like CNN, Vision Transformers, VAE, GAN, Diffusion .... for image data

    Jupyter Notebook 8 1

  3. GNN Public

    Jupyter Notebook

  4. Convex-Unconstrained-NonLinear-Optimization-Algorithms Public

    Analytical and numerical techniques like gradient descent, genetic algorithm, ... to solve a convex unconstrained nonlinear optimization problem from scratchh without using any python library

    Jupyter Notebook

  5. Tabular-Cross-Sectional-Modelling Public

    Implementation of algorithms such as normal equations, gradient descent, stochastic gradient descent, lasso regularization and ridge regularization from scratch and done linear as well as polynomia…

    Jupyter Notebook

  6. Time-Series-Modelling Public

    Performed literature survey on various architectures like FFNN, RNN, LSTM RNN, Gated RNN, and Transformers (SOTA Model) - unidirectional and bidirectional versions of all these, that can be used to…

    Jupyter Notebook