Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

Distribution transparent Machine Learning experiments on Apache Spark

Attentively Embracing Noise for Robust Latent Representation in BERT (COLING 2020)

Do models distinguish between declared-true and declared-false premises?

Reproducible research comparing GNN (GraphSAGE, GCN, GAT) vs ML baselines (XGBoost, RF) on Elliptic++ Bitcoin fraud detection. Features ablation experiments revealing when tabular models outperform graph neural networks.

Machine Learning analysis for an imbalanced dataset. Developed as final project for the course "Machine Learning and Intelligent Systems" at Eurecom, Sophia Antipolis

A multimodal deep learning project for classifying mental health-related memes, combining both textual and visual features.

🧠 Automated neural network ablation studies using LLM agents and LangGraph. Systematically remove components, test performance, and gain insights into architecture importance through an intelligent multi-agent workflow.

This study tries to compare the detection of lung diseases using xray scans from three different datasets using three different neural network architectures using Pytorch and perform an ablation study by changing learning rates. The dimensional understanding is visualised using t-SNE and Grad-CAM for visualisation of diseases in x-ray scans.

Re-implementation of the paper titled "Noise against noise: stochastic label noise helps combat inherent label noise" from ICLR 2021.

Phase zero of Artificial Neuroplasticity: Giving models self-editing capacity, through a trained triumvirate of three models; Analyzer / Trainee / Evaluator. The Analyzer uses TransformerLens to watch the Trainee. The Evaluator is the Review Board,, confirming the Trainee has become smarter than itself. This IS NOT implemented in this phase zero.

Ablation Study of CapsuleNetwork on TimeSeries

Intelligent layer pruning toolkit for LLMs featuring iterative optimization, self-healing algorithms, and comprehensive benchmarking.

🛠️ Optimize LLMs with advanced pruning strategies and real-time visualization for smaller, faster models without losing intelligence.

🔥 Emergent intelligence in autonomous trading agents through evolutionary algorithms. Testing zero-knowledge learning in cryptocurrency markets. Where intelligence emerges, not designed.

CNN implementation for CIFAR-10 image classification with hyperparameter ablation study.

Course project for AFLT class, Spring 2022: Exploring SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines

Generative Chatbot using Sequence-to-sequence Deep Learning (including 13 models) for ablation study

Design of an ablation study for a Machine Learning pipeline. The effect of preprocessing, model or postprocessing modules can be automatically tested.

Lightweight CNN for 28×28 grayscale multi-class image classification with augmentation & regularization.