Rahul Khurana's Projects
Advanced Deep Learning with Keras, published by Packt
Deep learning approach to compose one image in the style of another image
Original implementation of Spatially Invariant Attend, Infer, Repeat (SPAIR) in TensorFlow.
This project focuses on best practices of object-oriented programming, AWS AI Services, AWS DeepLens, AWS DeepRacer, and AWS DeepComposer.
Model to estimate the bike demand in future given the parameters as observed in the past.
Cat vs Non-cat Classifier using Numpy.
Find your hollywood celebrity look alike
Compact Bilinear Pooling (https://arxiv.org/abs/1511.06062) for TensorFlow
How to make a clean pull request on Github
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models
A List of frequently asked questions in Microsoft's Online Assessment and Interviews
Machine learning model to predict fraudulent credit card transactions
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Hands-on Deep Reinforcement Learning, published by Packt
Python implementation of Deep Learning book
Python (Pytorch) and Matlab (MatConvNet) implementations of CVPR 2021 Image Matching Workshop paper DFM: A Performance Baseline for Deep Feature Matching
Exploratory Data Analysis (EDA) for Californian housing data
FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery (TGRS)
Using Neuroevolution Of Augmenting Topologies trained an agent to play a clone of the Flappy Bird game
Platform for designing and evaluating Graph Neural Networks (GNN)
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Image to Image Search Engine
Combine multiple MNIST digits to create datasets with 100/1000 classes for few-shot learning/meta-learning
Publication-ready NN-architecture schematics.
Vision based techinque to evalute the distance between the camera and marker with over 90% accuracy