NumPy

hyperopt-sklearnhyperopt/hyperopt-sklearn

Hyperopt-sklearn automates hyperparameter optimization and model selection for scikit-learn machine learning pipelines.

boruta_pyscikit-learn-contrib/boruta_py

Python implementation of the Boruta all-relevant feature selection method with scikit-learn compatibility.

imodelscsinva/imodels

A Python package for concise, transparent, and accurate predictive modeling with sklearn-compatible interpretable models.

scikit-featurejundongl/scikit-feature

An open-source Python repository providing around 40 feature selection algorithms for machine learning applications.

SpearmintHIPS/Spearmint

A Bayesian optimization software package for automatically running experiments to minimize an objective in as few runs as possible.

empyricalquantopian/empyrical

A Python library for calculating common financial risk and performance metrics used in quantitative finance.

gnss-ins-simAceinna/gnss-ins-sim

An open-source GNSS/INS simulation tool that generates sensor data, runs navigation algorithms, and visualizes results for inertial navigation systems.

d3pymikedewar/d3py

A Python plotting library that generates interactive D3.js visualizations from pandas DataFrames.

Deeppyandersbll/deeppy

A Pythonic deep learning framework built on NumPy with optional CUDA acceleration.

ImagePyImage-Py/imagepy

An open-source, plugin-based image processing framework in Python that integrates with numpy-based libraries like scikit-image and OpenCV.

Intel(R) Extension for Scikit-learnintel/scikit-learn-intelex

A free software AI accelerator that speeds up scikit-learn applications by 10-100x on CPUs and GPUs with no code changes.

Brainstorm - Fast, flexible and fun neural networks.IDSIA/brainstorm

A discontinued Python neural network framework designed for fast, flexible experimentation with CPU and GPU backends.

fecon235rsvp/fecon235

A collection of Jupyter notebooks for financial economics, providing high-level APIs to retrieve, analyze, and visualize economic data from sources like FRED.

StarDiststardist/stardist

A Python library for 2D/3D object detection and instance segmentation in microscopy images using star-convex shapes.

dtaidistancewannesm/dtaidistance

A Python library with fast C implementations for computing Dynamic Time Warping and other time series distances.

pykittiutiasSTARS/pykitti

Python tools for working with the KITTI autonomous driving dataset, providing data loaders and utilities for computer vision and robotics.

eo-learnsentinel-hub/eo-learn

A Python framework for processing spatio-temporal satellite imagery and extracting features for machine learning applications.

adaptivepython-adaptive/adaptive

A Python library for parallel active learning of mathematical functions, intelligently sampling parameter spaces to minimize evaluations.

rpg_trajectory_evaluationuzh-rpg/rpg_trajectory_evaluation

A Python toolbox for quantitative evaluation of visual(-inertial) odometry trajectories using alignment methods and error metrics.

Brian2brian-team/brian2

A free, open-source Python simulator for spiking neural networks, designed for ease of use and flexibility.

Crabmuricoca/crab

A flexible, fast recommender engine for Python that integrates classic information filtering algorithms with scientific Python packages.

hebelhannes-brt/hebel

A GPU-accelerated deep learning library for Python using CUDA via PyCUDA, implementing neural networks with various training methods.

Emberelastic/ember

An open dataset and toolkit for training static PE malware machine learning models, featuring millions of labeled Windows executable samples.

Emberendgameinc/ember

An open dataset and toolkit for training static PE malware machine learning models, featuring extracted features from millions of Windows executable files.

rosshowdheera/rosshow

Visualize ROS topics directly in the terminal using Unicode/ASCII art for quick sensor debugging.

nnAudioKinWaiCheuk/nnAudio

An audio processing toolbox using PyTorch 1D convolutional neural networks for on-the-fly spectrogram generation with trainable kernels.

fastFMibayer/fastFM

A Python library implementing Factorization Machines with a scikit-learn compatible API for regression, classification, and ranking tasks.

Bpyuhlik/bpy

A Blender addon for visualizing, editing, filtering, rendering, and converting point cloud PLY files within the 3D viewport.

ParaTextwiseio/paratext

A C++ library for parallel text file reading with CSV support and Python bindings.

Neural Turing Machine in TensorFlowcarpedm20/NTM-tensorflow

TensorFlow implementation of Neural Turing Machines with LSTM controllers, supporting multiple read/write heads.

btgymKismuz/btgym

A scalable, event-driven backtesting library for reinforcement learning in algorithmic trading, built on Backtrader with OpenAI Gym API.

ikpyPhylliade/ikpy

A pure-Python inverse kinematics library for computing robot joint positions from end-effector poses.

ai-imu-drmbrossar/ai-imu-dr

A deep learning-enhanced Kalman filter for accurate vehicle dead reckoning using only an IMU sensor.

QANetNLPLearn/QANet

A TensorFlow implementation of QANet for machine reading comprehension on the SQuAD dataset.

scikit-multilearnscikit-multilearn/scikit-multilearn

A scikit-learn compatible Python module for multi-label classification tasks.

EvoJAXgoogle/evojax

A scalable, hardware-accelerated neuroevolution toolkit built on JAX for parallel training across TPUs/GPUs.