stevenabreu7

conceptors

Conceptors

adaptiveRL2

Adaptive (RL)²: representation learning for adaptive reinforcement learning. Using differentiable plasticity, state-space models, and deep RL.

automated-forward-thinking-keras

[AutoML] A Python Keras implementation to an automated adaption of the Forward Thinking algorithm proposed by Hettinger et al. in 2017

cnn_speaker_verification

[NLP] Implementing and Training of a Convolutional Neural Network to do Speaker Verification, i.e. decide whether two utterances (speech segments) were produced by the same speaker.

deep-rl-tennis

[Deep RL] Learning to play tennis using deep reinforcement learning in Unity's RL environment.

dvs_flow

Code for paper "Flow cytometry with event-based vision and spiking neuromorphic hardware"

handson_reservoir

Repository for paper "Hands-on reservoir computing" (NCE, 2022)

LavaNIR

NIR implementation for Lava-DL

Q-S5

Quantized version of the simplified state space model (S5). Using AQT and JAX.

SwiftSudoku

Sudoku Game implemented in Swift with Xcode with an AI solver that solves every Sudoku puzzle very fast!

stevenabreu7/handson_reservoir

Repository for paper "Hands-on reservoir computing" (NCE, 2022)

stevenabreu7/adaptiveRL2

Adaptive (RL)²: representation learning for adaptive reinforcement learning. Using differentiable plasticity, state-space models, and deep RL.

stevenabreu7/LavaNIR

NIR implementation for Lava-DL

stevenabreu7/luuk-msc-thesis

stevenabreu7/Q-S5

Quantized version of the simplified state space model (S5). Using AQT and JAX.

stevenabreu7/reservoir_benchmarking

Repository for benchmarking different physical reservoir computing systems.

stevenabreu7/dvs_flow

Code for paper "Flow cytometry with event-based vision and spiking neuromorphic hardware"

stevenabreu7/aestream

Efficient streaming of sparse event data supporting files, network I/O, GPU peripherals and neuromorphic protocols

stevenabreu7/annotated-s4

Implementation of https://srush.github.io/annotated-s4

stevenabreu7/aqt

stevenabreu7/conceptorsteering

Attempting to steer the behaviour of a GPT-2XL model using conceptors

stevenabreu7/conceptorsteering_old

stevenabreu7/dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

stevenabreu7/eventvision2023

stevenabreu7/expelliarmus

A Python/C library for decoding DVS encodings from binary files to structured NumPy arrays of events.

stevenabreu7/jax_dp_dqn

JAX-based implementation of a DQN with differential plasticity. 'tis a mess, work in progress

stevenabreu7/lava

A Software Framework for Neuromorphic Computing

stevenabreu7/lava-dl

Deep Learning library for Lava

stevenabreu7/lm-evaluation-harness

A framework for few-shot evaluation of language models.

stevenabreu7/mamba

Mamba SSM architecture

stevenabreu7/MoCapAct

A Multi-Task Dataset for Simulated Humanoid Control

stevenabreu7/neuroprimitives

neurocomputational primitives

stevenabreu7/NIR

Neuromorphic Intermediate Representation reference implementation

stevenabreu7/parse-ego4d

stevenabreu7/rag-state-soups

Using state soups for RAG with SSMs like Mamba. Part of the L&T topic area at Telluride 2024.

stevenabreu7/snntorch

Deep and online learning with spiking neural networks in Python

stevenabreu7/spyx

Spyx: Spiking Neural Networks in JAX

stevenabreu7/stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

stevenabreu7/stevenabreu7.github.io

Personal website. Forked from alshedivat/al-folio.

stevenabreu7/tt04-verilog-demo

Tiny neuromorphic takeout 2023!