Search Results for "backpropagation"
Sort By:
Showing 26 open source projects for "backpropagation"
View related business solutions-
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.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
Hivemind
Decentralized deep learning in PyTorch. Built to train models
...Its intended usage is training one large model on hundreds of computers from different universities, companies, and volunteers. Distributed training without a master node: Distributed Hash Table allows connecting computers in a decentralized network. Fault-tolerant backpropagation: forward and backward passes succeed even if some nodes are unresponsive or take too long to respond. Decentralized parameter averaging: iteratively aggregate updates from multiple workers without the need to synchronize across the entire network. Train neural networks of arbitrary size: parts of their layers are distributed across the participants with the Decentralized Mixture-of-Experts. ... -
2
LLM From Scratch
Build and train a GPT-style language model
LLM From Scratch is a hands-on educational workshop project that teaches developers how to build and train a GPT-style language model entirely from scratch using PyTorch. Instead of relying on high-level abstractions or prebuilt frameworks, the project walks users through implementing every core component manually, including tokenization, transformer architecture, training loops, and autoregressive text generation. The repository is intentionally simplified to focus on conceptual clarity,... -
3
AI Engineering from Scratch
Learn it. Build it. Ship it for others
...The project is structured into more than 20 phases and hundreds of lessons, covering topics that range from foundational mathematics to advanced systems such as large language models, retrieval pipelines, and multi-agent architectures. Each lesson emphasizes hands-on implementation, requiring learners to write core components such as backpropagation, tokenizers, and attention mechanisms themselves before using higher-level tools. The curriculum spans multiple programming languages, including Python, TypeScript, Rust, and Julia, which broadens the learner’s exposure to different ecosystems and performance considerations. It also focuses on producing tangible outputs such as prompts, agents, and reusable systems, allowing learners to build a real portfolio while studying. -
4
PyTorch Implementation of SDE Solvers
Differentiable SDE solvers with GPU support and efficient sensitivity
This library provides stochastic differential equation (SDE) solvers with GPU support and efficient backpropagation. examples/demo.ipynb gives a short guide on how to solve SDEs, including subtle points such as fixing the randomness in the solver and the choice of noise types. examples/latent_sde.py learns a latent stochastic differential equation, as in Section 5 of [1]. The example fits an SDE to data, whilst regularizing it to be like an Ornstein-Uhlenbeck prior process. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
PyTorch Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, etc.
TLlib is an open-source and well-documented library for Transfer Learning. It is based on pure PyTorch with high performance and friendly API. Our code is pythonic, and the design is consistent with torchvision. You can easily develop new algorithms or readily apply existing algorithms. We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please... -
6
DeepLearning Tutorial
Deep Learning Tutorial, Excellent Articles, Deep Learning Tutorial
...The project is designed as a knowledge collection that helps beginners understand neural networks, deep learning architectures, and fundamental machine learning concepts. It contains curated learning materials covering topics such as feedforward neural networks, activation functions, backpropagation algorithms, optimization methods, and convolutional neural networks. The repository organizes these materials into structured tutorials and references that allow readers to explore deep learning concepts progressively. Many of the resources include explanations of common model architectures used in computer vision and artificial intelligence. ... -
7
Deep Learning course
Slides and Jupyter notebooks for the Deep Learning lectures
Slides and Jupyter notebooks for the Deep Learning lectures at Master Year 2 Data Science from Institut Polytechnique de Paris. This course is being taught at as part of Master Year 2 Data Science IP-Paris. Note: press "P" to display the presenter's notes that include some comments and additional references. This lecture is built and maintained by Olivier Grisel and Charles Ollion. -
8
Keras TCN
Keras Temporal Convolutional Network
...MNIST, Adding Problem, Copy Memory, Word-level PTB...). Parallelism (convolutional layers), flexible receptive field size (possible to specify how far the model can see), stable gradients (backpropagation through time, vanishing gradients). The usual way is to import the TCN layer and use it inside a Keras model. The receptive field is defined as the maximum number of steps back in time from current sample at time T, that a filter from (block, layer, stack, TCN) can hit (effective history) + 1. The receptive field of the TCN can be calculated. ... -
9
micrograd
A tiny scalar-valued autograd engine and a neural net library
micrograd is a tiny, educational automatic differentiation engine focused on scalar values, built to show how backpropagation works end to end with minimal code. It constructs a dynamic computation graph as you perform math operations and then computes gradients by walking that graph backward, making it an approachable “from scratch” autograd reference. On top of the core autograd “Value” concept, the project includes a small neural network library that lets you define and train simple models with a PyTorch-like feel, including multilayer perceptrons. ... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
10
Neuroph is lightweight Java Neural Network Framework which can be used to develop common neural network architectures. Small number of basic classes which correspond to basic NN concepts, and GUI editor makes it easy to learn and use.
-
11
Multidimensional Neural Network
Multidimensional Neural Network
In Fully Connected Backpropagation Neural Networks, with many layers and many neurons in layers there is problem known as Gradient Vanishing Problem. Solution to lower its magnitude is to use Not Fully Connected Neural Network, when that is the case than with which neurons from previous layer neuron is connected has to be considered. The simplest solution would be to use Cartesian Coordinate System, and treat layers as one dimensional lines or two dimensional rectangles or three, four, five ... dimensional cuboids. ... -
12
DeepLearnToolbox
Matlab/Octave toolbox for deep learning
DeepLearnToolbox is a MATLAB / Octave toolbox for prototyping deep learning models. It provides implementations of feedforward neural networks, convolutional neural networks (CNNs), deep belief networks (DBNs), stacked autoencoders, convolutional autoencoders, and more. The toolbox includes example scripts for each method, enabling users to quickly experiment with architectures, training, and inference workflows. Although it's been flagged as deprecated and no longer actively maintained, it... -
13
LensOSX
LensOSX: the light, efficient network simulator
Lens is the light, efficient network simulator, written by Doug Rohde. LensOSX is a native MacOSX port of Lens that runs on MacOSX 10.5 or higher, created by Harm Brouwer, Daniel de Kok and Hartmut Fitz. -
14
OSXtlearn
OSXtlearn: tlearn for MacOSX
tlearn is a backpropagation neural network simulator, written by Jeff Elman. xtlearn is a version of tlearn for the X Window System. OSXtlearn is xtlearn wrapped in a MacOSX application bundle that runs ons MacOSX 10.5 or higher and that requires XQuartz. OSXtlearn is created by Harm Brouwer. -
15
eANN
eANN is an implementation of several kind of neural networks.
eANN is an implementation of several kind of neural networks written with the intention of providing a (hopefully) easy to use, and easy to modify, OOP source code. It is possible to have several different sized networks running simultaneously, each functioning independently of the others or acting as inputs between them. It also easy to modify the structure so that neurons (or even whole layers) can be created/pruned during simulation allowing dynamic expansion/contraction of the network. -
16
cognity
A neural network library for Java.
Cognity is an object-oriented neural network library for Java. It's goal is to provide easy-to-use, high level architecture for neural network computations along with reasonable performance. -
17
This project provides a set of Python tools for creating various kinds of neural networks, which can also be powered by genetic algorithms using grammatical evolution. MLP, backpropagation, recurrent, sparse, and skip-layer networks are supported.
-
18
Nen
neural network implementation in java
3-layer neural network for regression and classification with sigmoid activation function and command line interface similar to LibSVM. Quick Start: "java -jar nen.jar" -
19
PlexBench is a cross-platform, web-enabled, analysis tool that is driven by a scalable backpropagation feed-forward neural network. It uses embedded Perl for scripting and is written in the style of an in-process Component Object Model (COM) C++ program.
-
20
backprop1 provides a simple three layer backpropagation neural network implemented in java. There are three demo programs to perform point classification, the XOR problem and character recognition.
-
21
-
22
Breeze a multiple class model neural network development system. Network models include multi-threaded Backpropagation and Radial Basis Function Networks, for time series prediction.
-
23
RL Poker is a study project Java implementation of an e-soft on-policy Monte Carlo Texas Hold'em poker reinforcement learning algoritm with a feedforward neural network and backpropagation. It provides a graphical interface to monitor game rounds.
-
24
NeuroBox is an .NET OOP Library to generate, propagate and train complex neuronal networks with technologies like backpropagation with weight decay, momentum term, manhattan training, flatspot elimination etc.
-
25
Lightweight backpropagation neural network in C. Intended for programs that need a simple neural network and do not want needlessly complex neural network libraries. Includes example application that trains a network to recognize handwritten digits.