Language Breakdown
Lines of code distribution across 12 owned repositories
T-Shaped Developer
T-shapedDeep in Jupyter Notebook with broad versatility
Collaboration Network
Global Impact visualization
Repos
16
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Mohamed Reda Nkira
@med-reda-nk
Ayman Zaidane
@eayzaid
Khalil Ait Nouisse
@khalil-nouisse
Adam El Madani
@Adameelmadani
ibtihajml1
@ibtihajml1
Top Repositories
Implementation of LightGBM (NIPS 2017). A Highly Efficient GBDT utilizing Gradient-based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB) for high-dimensional sparse data.
This repository includes basic **image processing** techniques like pixel modifications, cropping, resizing, flipping, rotation, and applying filters such as Gaussian blur and Laplacian.
A hybrid long-term memory architecture for AI agents, integrating episodic, semantic, and procedural memory for persistent context and cross-session coherence.
A high-performance, scalable data processing pipeline for LLM pre-training. This repository provides a modular framework for large-scale tokenization, binary indexing using Datatrove, and optimized distributed data loading in PyTorch. Designed for high-throughput training environments and efficient handling of massive datasets.
Multi-Agent Reinforcement Learning framework for stealth swarm infiltration in 3D environments. This project simulates high-fidelity radar physics, including RCS modeling, SNR-based detection, and probabilistic noise floors to optimize collective swarm survival and infiltration ratios
CPP-neural-network is a lightweight, educational project built to demystify deep learning. By implementing core concepts like gradient descent and matrix calculus entirely in C++, this repo serves as a step-by-step guide to understanding how neural networks function under the hood.
MarocExplorer is a geographic prediction project that estimates the GPS coordinates (latitude, longitude) of an image taken in Morocco, leveraging both its visual content and metadata associated with the corresponding city (climate, architecture, altitude, environment type, etc.)
The project aims to develop a predictive maintenance system based on the temporal DNA fingerprint of industrial machines. It enables the detection of anomalies before failures occur, using MATLAB simulations and validation of predictive models.
Open Source Impact
Contributions to external projects
