Pinned Repositories
Multi-task-learning-on-MNIST-fashion-data
Building a MTL network with hard parameter sharing. I explore the FASHION MNIST dataset and code up my own MTL model, and consider the pros and cons of MTL compared to single task learning.
Mining-Opinion-Features-in-Customer-Reviews
The task is Opinion Mining; it is closely related to sentiment analysis and involves using techniques related to information extraction
Spam-Classifier
Given a set of testing data, with a bag of words encoding on each email message. We end up with a matrix of messages and their features, as binary encoded values. That is, for each email message, a feature x will be encoded to a 1 if it is present in an email message. Each email has 54 features, the first column of data being the class (0,1) indicating that it is spam or not.
Sudoku-Solver
The approach to building an algorithm for solving the sudoku, started by reading the section Contraction Satisfaction Problems from (Norvig, 2020).
Decision-Tree
Building Decision tree from scratch using Pandas data structure. I used Information gain for measuring purity in group of observations.
Genetic-Algorithms
Solve Eight queens state puzzle using genetic algorithms. then enhance the basic implementation and optimise it to handle N queen. Results are recorded in the attached report
AdaFace
AnasR1986
Config files for my GitHub profile.
CLUSTERING-OF-COPENHAGEN-TRANSPORT-STATIONS
CLUSTERING OF COPENHAGEN STATIONS
Cones-V2
rezkanas's Repositories
rezkanas/rezkanas
rezkanas/HPSv2
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
rezkanas/hugging-chat-api
HuggingChat Python API🤗
rezkanas/AdaFace
rezkanas/Mix-of-Show
NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
rezkanas/tifa
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
rezkanas/Cones-V2
rezkanas/fastcomposer
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
rezkanas/lambda-eclipse-inference
Official PyTorch implementation of "λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space"
rezkanas/PickScore
rezkanas/traing_arrow_through_racetrack
Training an Arrow to go through a predefined Bended Racetrack using On-Policy First-Visit Monte-Carlo Control, Sarsa, and Q-Learning algorithms.
rezkanas/RL_Bipedal_Robot
Teaching a Simulated Bipedal Robot to Navigate an Uneven Terrain using a model-free, online, off-policy reinforcement learning method
rezkanas/Multi-task-learning-on-MNIST-fashion-data
Building a MTL network with hard parameter sharing. I explore the FASHION MNIST dataset and code up my own MTL model, and consider the pros and cons of MTL compared to single task learning.
rezkanas/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
rezkanas/Decision-Tree
Building Decision tree from scratch using Pandas data structure. I used Information gain for measuring purity in group of observations.
rezkanas/Genetic-Algorithms
Solve Eight queens state puzzle using genetic algorithms. then enhance the basic implementation and optimise it to handle N queen. Results are recorded in the attached report
rezkanas/deepdream
rezkanas/Spam-Classifier
Given a set of testing data, with a bag of words encoding on each email message. We end up with a matrix of messages and their features, as binary encoded values. That is, for each email message, a feature x will be encoded to a 1 if it is present in an email message. Each email has 54 features, the first column of data being the class (0,1) indicating that it is spam or not.
rezkanas/Mining-Opinion-Features-in-Customer-Reviews
The task is Opinion Mining; it is closely related to sentiment analysis and involves using techniques related to information extraction
rezkanas/Recommender-System-Architecture
This provides an insight in building an online database AI-enabled system
rezkanas/Sudoku-Solver
The approach to building an algorithm for solving the sudoku, started by reading the section Contraction Satisfaction Problems from (Norvig, 2020).
rezkanas/Enigma
A Python simulation of the famous Enigma Machine used by the Germans in WW2. The project also includes a code cracking solutions, mimicking the Bombe machine developed by the Polish and Alan Turing, to eventually crack the Engima code.
rezkanas/rezkanas.github.io
personal webpage
rezkanas/AnasR1986
Config files for my GitHub profile.
rezkanas/CLUSTERING-OF-COPENHAGEN-TRANSPORT-STATIONS
CLUSTERING OF COPENHAGEN STATIONS