A framework for the comparative training and evaluation of statistical and deep learning models for multi-feature categorical sequence modeling, utilizing feature fusion and automated with MLflow and Optuna integration.

Code Repository for Liquid Time-Constant Networks (LTCs)

PyxLSTM is a Python library that provides an efficient and extensible implementation of the Extended Long Short-Term Memory (xLSTM) architecture. xLSTM enhances the traditional LSTM by introducing exponential gating, memory mixing, and a matrix memory structure, enabling improved performance and scalability for sequence modeling tasks.

Pytorch implementation of Simplified Structured State-Spaces for Sequence Modeling (S5)

Liquid Structural State-Space Models

Implementation of GateLoop Transformer in Pytorch and Jax

An unofficial implementation of "TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest" in Tensorflow

sequence modeling lstm model

Repo to reproduce the First-Explore paper results

Applied Ai (Papers, Articles & Videos, applied in production with results)

Source code for "A Lightweight Recurrent Network for Sequence Modeling"

Tensorflow implementation of Long Short-Term Memory model for audio synthesis used for thesis

Audio and Music Synthesis with Machine Learning

Transformer/BERT models trained on the Breakthrough Listen Kaggle dataset.

Caption Images with Machine Learning

A Generative Model for Audio in the Frequency Domain

Sentiment analysis performed using a pre-trained BERT model on Mac Miller's complete discography.

The course studies fundamentals of distributed machine learning algorithms and the fundamentals of deep learning. We will cover the basics of machine learning and introduce techniques and systems that enable machine learning algorithms to be efficiently parallelized.

Contains various architectures and novel paper implementations for Natural Language Processing tasks like Sequence Modelling and Neural Machine Translation.