machine-learning-research

A collection of research papers on decision, classification and regression trees with implementations.

PDF-derived institutional affiliations for 5,356 ICLR 2026 accepted papers — full pipeline (scrape → parse → render), clean dataset (CSV + XLSX), and treemap charts.

Stock price prediction model built using BERT and regression model trained on textual financial news data.

Lernd is ∂ILP (dILP) framework implementation based on Deepmind's paper Learning Explanatory Rules from Noisy Data.

This is the project repo associated with the paper "Disentangling and Integrating Relational and Sensory Information in Transformer Architectures" by Awni Altabaa, John Lafferty

B.Sc. Thesis Deep Learning & NLP research on Medical Image Captioning

Experimental embedding research on semantic attention, Fourier token mixing, and branch-disagreement diagnostics.

Financial transactions fraud detection using ML (research, experimentation and deployment via Google Cloud)

This Guide book is written with the intention of helping researchers and engineers working in machine learning domains to publish reproducible research.

Transformer interpretability research framework for circuit discovery, sparse features, and controlled residual-stream interventions.

Deep Classiflie is a framework for developing ML models that bolster fact-checking efficiency. As a POC, the initial alpha release of Deep Classiflie generates/analyzes a model that continuously classifies a single individual's statements (Donald Trump) using a single ground truth labeling source (The Washington Post). For statements the model d…

Curated Applied Scientist & Research Engineer roles at AI labs and companies, with salaries, 2026. By Landed.

Holographic Laplace Attention: Decoupling data retrieval and content transmission. Content-conditioned phase rotation (Q/K) + bidirectional Laplace gating (K/V) + salience bias

TensorOps - A Work-In-Progress Autodiff Library

Deep_classiflie_db is the backend data system for managing Deep Classiflie metadata, analyzing Deep Classiflie intermediate datasets and orchestrating Deep Classiflie model training pipelines. Deep_classiflie_db includes data scraping modules for the initial model data sources. Deep Classiflie depends upon deep_classiflie_db for much of its anal…

A 60-day roadmap to learn Machine Learning Research through experiments, methodology, hypothesis testing, and reproducible projects.

Geometric initialization for deep networks: narrow cone on input, hierarchy of amplitudes, gradual expansion through layers.

🫀 Screening for cardiac pathology from smartphone phonocardiograms. A research pipeline and its findings: data-centric methodology, the CardioNet architecture family, real metrics, and honest limitations. Research prototype, not a medical device.

PyTorch implementation of "Train for the Worst, Plan for the Best." Investigating adaptive token ordering in Masked Diffusion Models (MDMs) to sidestep hard subproblems and elicit reasoning in discrete domains.

A bit-native predictive machine: next-bit (0/1) prediction via a learned binary-address content-addressable memory. No tokens, no embeddings — vocabulary of 2. An honest, adversarially-verified research log.