Binary and Categorical Focal loss implementation in Keras.

Code for ICCV2019 "Symmetric Cross Entropy for Robust Learning with Noisy Labels"

A PyTorch implementation of U-Net for aerial imagery semantic segmentation.

Pytorch Implementations of Common modules, blocks and losses for CNNs specifically for segmentation models

Implementation of key concepts of neuralnetwork via numpy

A Feed Forward Neural Network which a ReLU activation, Cross Entropy Loss & Adam Optimizer

Decision Tree Implementation from Scratch

Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

Simple Implementation of Gradient Boosted Trees

We classified Stack Overflow Python questions from 2008-2016 with Natural Language Processing and Deep Learning. Using Regular Expressions, we removed HTML tags and punctuation. We also utilized spaCy to tokenize, lemmatize and remove stop words. Using Keras, we built a 4 layered artificial neural network with a 20% dropout rate using relu and s…

C codes for the Arificial Intelligence Course and algorithms.

Maths behind machine learning and some implementations from scratch.

Breast Cancer Classification with Logistic Regression

full visualization of netflix and movielense datasets with 89% accuraccy item2vec

Digital Image Processing Course | Home Works Design| Fall 2021 | Dr. MohammadReza Mohammadi

Evaluated the word vectors learned from both nce and cross entropy loss functions using word analogy tests

In the project, the aim is to generate new song lyrics based on the artist’s previously released song’s context and style. We have chosen a Kaggle dataset of over 57,000 songs, having over 650 artists. The dataset contains artist name, song name, a link of the song for reference & lyrics of that song. We tend to create an RNN character-level la…

A classifier to differentiate between Cat and Non-Cat Images

Comparison of common loss functions in PyTorch using MNIST dataset

Neural network-based character recognition using MATLAB. The algorithm does not rely on external ML modules, and is rigorously defined from scratch. A report is included which explains the theory, algorithm performance comparisons, and hyperparameter optimization.