Search Results for "learning" - Page 94
Sort By:
Showing 4736 open source projects for "learning"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
FARM
Fast & easy transfer learning for NLP
FARM makes Transfer Learning with BERT & Co simple, fast and enterprise-ready. It's built upon transformers and provides additional features to simplify the life of developers: Parallelized preprocessing, highly modular design, multi-task learning, experiment tracking, easy debugging and close integration with AWS SageMaker. With FARM you can build fast proofs-of-concept for tasks like text classification, NER or question answering and transfer them easily into production. ... -
2
YOLOv4-large
Scaled-YOLOv4: Scaling Cross Stage Partial Network
YOLOv4-large is an open-source implementation of the Scaled-YOLOv4 object detection architecture, designed to improve both the accuracy and scalability of real-time computer vision models. The project provides a PyTorch implementation of the Scaled-YOLOv4 framework, which extends the original YOLOv4 architecture using Cross Stage Partial (CSP) networks and new scaling techniques. Unlike earlier object detection systems that only scale depth or width, this architecture scales multiple aspects... -
3
Microsoft Bot Framework SDK
Tool for building conversation applications
Bot Framework provides the most comprehensive experience for building conversation applications. With the Bot Framework SDK, developers can build bots that converse free-form or with guided interactions including using simple text or rich cards that contain text, images, and action buttons. Developers can model and build sophisticated conversation using their favorite programming languages including C#, JS, Python and Java or using Bot Framework Composer, an open-source, visual authoring... -
4
Easy Agent Simulation
Java-based agent simulation platform
EAS is a Java-based simulation platform, developed as part of a research project at the Karlsruhe Institute of Technology. It comes with a broad range of pre-developed simulation scenarios, ranging from virtual agents acting in abstract environments to agents with a spatial representation in 2D or 3D. It is built upon a novel architecture using a separate "plugin layer" to communicate between the simulation engine and the simulated model. This allows to flexibly add or remove... -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
SimCSE
SimCSE: Simple Contrastive Learning of Sentence Embeddings
SimCSE (Simple Contrastive Learning of Sentence Embeddings) is a machine learning framework for training sentence embeddings using contrastive learning. It improves representation learning for NLP tasks. -
6
the hotdog web browser
The hotdog web browser and browser engine
the hotdog web browser project is a hobbyist web browser and layout engine written entirely from scratch in Go to explore how browsers work under the hood, implementing core components like an HTML parser, CSS rendering, UI toolkit, networking, and layout logic without relying on heavy external dependencies. It’s far from being a complete or spec-compliant browser, but it’s designed to be a learning platform and experimental codebase for anyone curious about browser internals and rendering architecture. The repository includes custom named modules such as ketchup for HTML parsing, mayo for CSS rendering, and a minimal OpenGL/GLFW-based UI toolkit termed mustard, among others. Because it’s handcrafted with minimal dependencies (only OpenGL and GLFW outside the standard library), it emphasizes understanding every part of the browser stack. ... -
7
VITS
Conditional Variational Autoencoder with Adversarial Learning
VITS is a foundational research implementation of “VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech,” a well-known neural TTS architecture. Unlike traditional two-stage systems that separately train an acoustic model and a vocoder, VITS trains an end-to-end model that maps text directly to waveform using a conditional variational autoencoder combined with normalizing flows and adversarial training. -
8
RegexAssistant
Regex Windows GUI app to help learn, create,& test Regular Expressions
RegexAssistant is a Regex GUI application to help learn, create, and test Regular Expressions. It's an open source stand alone Windows application. RegexAssistant is great for beginners and intermediate-advanced regex users. -It helps beginners to learn regex by providing examples and token cheat-sheet. -Intermediate-advanced users can use RegexAssistant to test complex expressions. -
9
course-v3
The 3rd edition of course.fast.ai
course-v3 repository contains the complete learning materials for the third edition of the Practical Deep Learning for Coders course developed by the fast.ai research group. The repository includes Jupyter notebooks, lesson materials, datasets, and supporting documentation used in the course to teach modern deep learning techniques. The course emphasizes a top-down approach to learning artificial intelligence, where students begin by building practical models and later study the underlying theory and mathematics. ... -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
10
YApi
A locally deployable, visual interface management platform
...Friendly interface documentation, WebSocket-based multi-person collaboration interface editing function and postman-like testing tools, allowing multi-person collaboration to multiply development efficiency. Based on Mockjs, easy to use and powerful. You can easily write interfaces by learning some simple mock template rules, which will greatly improve the efficiency of defining interfaces, and you don't need to worry about writing mock data: all data can be randomly generated in real-time. The generated Mock data can be used directly with ajax requests or through server proxy (no need to modify a line of code in the project). -
11
tensorflow_template_application
TensorFlow template application for deep learning
tensorflow_template_application is a template project that demonstrates how to structure scalable applications built with TensorFlow. The repository provides a standardized architecture that helps developers organize machine learning code into clear components such as data processing, model training, evaluation, and deployment. Instead of focusing on a specific algorithm, the project emphasizes software engineering practices that make machine learning systems easier to maintain and extend. The template includes configuration files, scripts, and project structures that help teams build reproducible experiments and production-ready pipelines. ... -
12
deep-learning-for-image-processing
deep learning for image processing including classification
deep-learning-for-image-processing is an extensive educational repository covering practical deep learning methods for computer vision. It organizes implementations, explanations, presentation files, and video lessons around major neural network architectures. The material teaches both model structure and training workflows, with examples built in PyTorch and TensorFlow through Keras. -
13
neurojs
A JavaScript deep learning and reinforcement learning library
neurojs is a JavaScript framework designed to enable deep learning and reinforcement learning directly within web environments. The library provides a full machine learning framework implemented in JavaScript that can run inside browsers or Node.js environments. It focuses particularly on reinforcement learning algorithms, enabling developers to create intelligent agents that learn through interaction with simulated environments. -
14
libpostal
A C library for parsing/normalizing street addresses around the world
A C library for parsing/normalizing street addresses around the world. Powered by statistical NLP and open geo data. libpostal is a C library for parsing/normalizing street addresses around the world using statistical NLP and open data. The goal of this project is to understand location-based strings in every language, everywhere. Addresses and the locations they represent are essential for any application dealing with maps (place search, transportation, on-demand/delivery services,... -
15
TinyGL
The penultimate portable graphics library
tinygl is a lightweight, software-based OpenGL implementation originally written by Fabrice Bellard and modified here for modern learning and development purposes. It implements a subset of OpenGL 1.x features and provides a minimal yet functional rendering pipeline with no reliance on graphics hardware. tinygl is an ideal resource for educational purposes, embedded development, or rendering in software-only environments. Its simplicity and compact codebase allow developers to study how 3D graphics APIs work under the hood. -
16
AliceMind
ALIbaba's Collection of Encoder-decoders from MinD
This repository provides pre-trained encoder-decoder models and its related optimization techniques developed by Alibaba's MinD (Machine IntelligeNce of Damo) Lab. Pre-trained models for natural language understanding (NLU). We extend BERT to a new model, StructBERT, by incorporating language structures into pre-training. Specifically, we pre-train StructBERT with two auxiliary tasks to make the most of the sequential order of words and sentences, which leverage language structures at the... -
17
ml-design-patterns
Source code accompanying O'Reilly book: Machine Learning Design
The ml-design-patterns repository contains the source code and examples that accompany the book “Machine Learning Design Patterns,” providing practical implementations of reusable solutions for common challenges in machine learning systems. It organizes patterns into categories such as data representation, problem framing, and model training, helping practitioners understand how to structure ML pipelines effectively. The repository includes implementations of techniques like feature hashing, embeddings, feature crosses, and multimodal inputs, which are essential for handling diverse data types. ... -
18
Machine Learning Beginner
Machine Learning Beginner Public Account Works
Machine Learning Beginner targets newcomers who are just getting started with machine learning and need a gentle, guided path. It introduces the core vocabulary and the mental map of supervised and unsupervised learning before moving into simple algorithms. The materials prioritize conceptual clarity, then progressively add code to solidify understanding. -
19
TensorFlow.js models
Pretrained models for TensorFlow.js
This repository hosts a set of pre-trained models that have been ported to TensorFlow.js. The models are hosted on NPM and unpkg so they can be used in any project out of the box. They can be used directly or used in a transfer learning setting with TensorFlow.js. To find out about APIs for models, look at the README in each of the respective directories. In general, we try to hide tensors so the API can be used by non-machine learning experts. New models should have a test NPM script. You can run the unit tests for any of the models by running "yarn test" inside a directory. ... -
20
workshops_project
Workshops is an open source, simple, dead-lightweight LMS
Workshops is an open source, simple, dead-lightweight LMS (Learning Management System) application programmed in Python (version 3.8.x) with Django (version 2.2.x) web framework which main purpose is to make a standarized way to share knowledge via courses in a slide-based view in browser powered by remark javascript library, easy to create, edit, delete and show your courses using simple markdown and html if necessary. -
21
Pytorch Points 3D
Pytorch framework for doing deep learning on point clouds
...Task driven implementation with dynamic model and dataset resolution from arguments. Core implementation of common components for point cloud deep learning - greatly simplifying the creation of new models. 4 Base Convolution base classes to simplify the implementation of new convolutions. Each base class supports a different data format. -
22
Open Application Model
Open Application Model (OAM)
Open Application Model (OAM) is a set of standard yet higher-level abstractions for modeling cloud-native applications on top of today's hybrid and multi-cloud environments. Focused on application rather than container or orchestrator, Open Application Model brings modular, extensible, and portable design for defining application deployment with higher level API. This is the key to enabling simple, consistent yet robust application delivery across hybrid environments including Kubernetes,... -
23
Pwnagotchi
Deep Reinforcement learning instrumenting bettercap for WiFi pwning
...This material is collected on disk as PCAP files containing any form of handshake supported by hashcat, including full and half WPA handshakes as well as PMKIDs. Instead of merely playing Super Mario or Atari games like most reinforcement learning based “AI” (yawn), Pwnagotchi tunes its own parameters over time to get better at pwning WiFi things in the real world environments you expose it to. To give hackers an excuse to learn about reinforcement learning and WiFi networking, and have a reason to get out for more walks. -
24
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
The Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unspooling, and broadcasting operations for sparse tensors. The Minkowski Engine supports various functions that can be built on a sparse tensor. We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to... -
25
SRU
Training RNNs as Fast as CNNs
Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations. In this work, we propose the Simple Recurrent Unit (SRU), a light recurrent unit that balances model capacity and scalability. SRU is designed to provide expressive recurrence, enable highly parallelized implementation, and comes with careful initialization to facilitate the training of deep models. We demonstrate the effectiveness of SRU on multiple NLP tasks. SRU...