Skip to content

Avatar

deekshant
data scientist

d33kshant

I am a data scientist with a masters in artificial intelligence and a bachelors in computer science. specialized and experienced in ai and machine learning based automation and analysis, I have very keen interest in ai & ml, open source and software development.

Experience

  • Novartis Hyderabad, India


    Data Scientist

    2025 - Present

    Data Science Intern

    2024 - 2025

Projects

I prefer project based learning thats why I always try to apply my learning on small or big projects. Over the years I've worked on many projects related to Web, AI and Open Source.

Pinned Projects

  •   Music Generator with LSTM


    A jazz music generator for an indie game using LSTM neural network

    Open In Google Colab

  •   Stock Price Prediction with LSTM


    A Long Short-Term Memory (LSTM) neural network to predict stock prices

    Open In Google Colab

  •   HMM A Minimal Language Model


    Probability based language modeling to create a very minimal language model

    View    Open In Google Colab

  •   Snake Game Bot


    A bot that plays classic snake game with reinforcement learning

    Read    Open In Google Colab

Explore More

Blogs

I do not write alot but often share my learning, opinions or experience time to time. I use AI to rectify and summaries the content to make it more expressive

Recent Blogs

  •   Introduction to Machine Learning


    Have you ever wondered how Netflix knows exactly what show you might want to watch next? Or how your email automatically filters spam messages? Or maybe how your phone recognizes your face? All of these technological wonders are powered by machine learning.

  •   Implementing Convolutional Neural Networks using Tensorflow


    Convolutional Neural Networks (CNNs) are a class of deep learning models that excel at working with image data. Instead of processing each pixel independently (like in a fully connected neural network), CNNs use filters (or kernels) to scan across the image, capturing spatial hierarchies and local patterns like edges, textures, and shapes.

  •   Implementing Principal Component Analysis (PCA) from Scratch


    Principal Component Analysis (PCA) is a widely used technique for reducing the dimensionality of datasets while retaining the most important information. It does this by transforming correlated variables into a smaller set of uncorrelated variables called principal components.

Read More