"One Hidden Layer Neural Network" from Scratch
"Deep Neural Network" from Scratch
This repository implements a vector search solution based on image and text embeddings. Users can search for similar products using an image or a textual description.
"CNN" from Scratch
A brand new programming language designed for developers with diverse coding interests!
"Logistic Regression" from Scratch
ZynkPy is an Interpreted programming language and a Compiled (because i'm going to support that i the future)
Includes the codes and report for Take Home Exam 2 of the CENG483 course (Introduction to Computer Vision). The purpose of this THE is to gain insight related to harris interest point detection.
Write the K Nearest Neighbors classifier from scratch in Python. Test it on email spam classification dataset.
Includes the codes and report for Take Home Exam 1 of the CENG483 course (Introduction to Computer Vision). The purpose of the THE is familiarize ourselves with the concept of various types of histogram.
Neural Networks: Zero to Hero
Over several weeks, I manually implemented every stage of a convolutional neural network using only NumPy—without relying on TensorFlow or PyTorch. The network uses Xavier and He initialization, supports both Leaky ReLU and standard ReLU activations, and applies L2 regularization with exponential learning rate decay to improve generalization.
This repository explores building a character-level transformer decoder in PyTorch, similar to GPT while focusing more on understanding individual components. My goal is to gain deep transformer knowledge and see if character-level learning improves handling of unseen words. The code allows for hyperparameter tuning and experiment customization.
A minimal NumPy-based implementation of a 3-layer convolutional neural network (CNN) from scratch — including custom forward and backward passes for conv, ReLU, pooling, affine, and softmax layers. Perfect for learning how CNNs actually work under the hood.
This is the source code of the work for Assignment-2, Statistical Methods in AI, 5th Semester, IIITH, '22
MNIST Digit Detector Model using only Numpy
neural network from scratch with mnist dataset
Collection of implementations from scratch (mostly ML)
Binary classification machine learning algorithm using only Numpy
Add a description, image, and links to the from-scratch-in-python topic page so that developers can more easily learn about it.
To associate your repository with the from-scratch-in-python topic, visit your repo's landing page and select "manage topics."