Search Results for "neuron"
Sort By:
Showing 66 open source projects for "neuron"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
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
AWS Neuron
Powering Amazon custom machine learning chips
AWS Neuron is a software development kit (SDK) for running machine learning inference using AWS Inferentia chips. It consists of a compiler, run-time, and profiling tools that enable developers to run high-performance and low latency inference using AWS Inferentia-based Amazon EC2 Inf1 instances. Using Neuron developers can easily train their machine learning models on any popular framework such as TensorFlow, PyTorch, and MXNet, and run it optimally on Amazon EC2 Inf1 instances. ... -
2
Neuron AI
The PHP Agentic Framework to build production-ready AI driven apps
Neuron AI is a PHP agentic framework for building production-ready AI applications that connect models, memory, vector databases, and tools into working agents. It is designed for developers who want to create systems such as RAG pipelines, multi-agent workflows, and business process automations without having to hand-build every integration from scratch. -
3
Automated Interpretability
Code for Language models can explain neurons in language models paper
The automated-interpretability repository implements tools and pipelines for automatically generating, simulating, and scoring explanations of neuron (or latent feature) behavior in neural networks. Instead of relying purely on manual, ad hoc interpretability probing, this repo aims to scale interpretability by using algorithmic methods that produce candidate explanations and assess their quality. It includes a “neuron explainer” component that, given a target neuron or latent feature, proposes natural language explanations or heuristics (e.g. ... -
4
Transformer Debugger
Tool for exploring and debugging transformer model behaviors
...It automatically identifies and explains the most influential components, highlights activation patterns, and maps relationships across circuits within the model. The tool includes both a React-based neuron viewer for exploring model components and a backend activation server for running inferences and serving data. -
Catch Bugs Before Your Customers DoMove from alert to fix before users notice. AppSignal monitors errors, performance bottlenecks, host health, and uptime—all from one dashboard. Instant notifications on deployments, anomaly triggers for memory spikes or error surges, and seamless log management. Works out of the box with Rails, Django, Express, Phoenix, Next.js, and dozens more. Starts at $23/month with no hidden fees.
-
5
PowerInfer
High-speed Large Language Model Serving for Local Deployment
...This hybrid execution strategy significantly reduces memory bottlenecks and improves overall inference speed. PowerInfer incorporates specialized algorithms and sparse operators to manage neuron activation patterns and minimize data transfers between hardware components. As a result, it enables powerful language models to run on consumer hardware while achieving performance comparable to more expensive server-grade systems. -
6
SpikingJelly
SpikingJelly is an open-source deep learning framework
...This makes it especially relevant for researchers interested in biologically inspired computing, event-driven processing, and energy-efficient AI systems. The framework includes neuron models, surrogate gradient training methods, encoding strategies, network components, and utilities for simulation and experimentation, allowing users to develop a wide variety of spiking architectures. It also supports integration with familiar PyTorch workflows, which lowers the barrier for machine learning practitioners who want to explore spiking approaches without abandoning mainstream tooling. -
7
BertViz
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
...The head view visualizes attention for one or more attention heads in the same layer. It is based on the excellent Tensor2Tensor visualization tool. The model view shows a bird's-eye view of attention across all layers and heads. The neuron view visualizes individual neurons in the query and key vectors and shows how they are used to compute attention. -
8
NanoNeuron
NanoNeuron is 7 simple JavaScript functions
Nano-Neuron is a didactic project that reduces the idea of a neuron to a handful of tiny JavaScript functions so learners can see “learning” in action without heavy frameworks. It demonstrates how a scalar input can be linearly transformed with a weight and bias, then adjusted via gradient updates to fit a simple mapping such as Celsius-to-Fahrenheit conversion. -
9
snntorch
Deep and online learning with spiking neural networks in Python
...This allows researchers to train spiking neural models using familiar deep learning workflows while taking advantage of GPU acceleration and automatic differentiation. snnTorch provides implementations of common spiking neuron models, surrogate gradient training methods, and utilities for handling temporal neural dynamics. Because spiking neural networks operate over time and encode information through spike timing, the library includes tools for simulating temporal behavior. -
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
10
emanote
Emanate a structured view of your plain-text notes
Emanate a structured view of your plain-text notes. Create beautiful websites such as personal webpage, blog, wiki, Zettelkasten, notebook, knowledge-base, documentation, etc. from future-proof plain-text notes and arbitrary data, with live preview that updates in real-time. Emanote is the spiritual successor to neurons based on Ema. Emanote is a Haskell software. Thanks to Nix, this repository is pre-configured to provide a delightful development experience with full IDE support in Visual... -
11
NeuronetExperimenter
NeuronetExperimenter simulates the activity of biological neurons
...The software makes it easy to investigate the behaviors of large, complex, neural networks, especially when starting from XPPAUT models (http://www.math.pitt.edu/~bard/xpp/xpp.html). The software is very flexible and allows users to develop multiple neuron types with different constituent differential equations describing their behavior. Any of these neuron types can be included in a network together where each neuron has its own unique set of parameters that can be changed during the course of the simulation. -
12
DDE-BIFTOOL
Bifurcation analysis for delay-differential equations
DDE-BIFTOOL is a set of routines for performing numerical bifurcation analysis of delay-differential equations, running in Matlab or Octave[2]. It was originally created by Koen Engelborghs at KU Leuven (Belgium). [1] Tutorial demo <http://ddebiftool.sourceforge.net/demos/neuron/html/demo1_simple.html> shows the output of an illustrative demo. <http://ddebiftool.sourceforge.net> links to documentation, a list of contributors and current maintainers. The original DDE-BIFTOOL webpage at KU Leuven [1] stores versions up to 3.0 and their documentation. [1] <http://twr.cs.kuleuven.be/research/software/delay/ddebiftool.shtml> [2] <https://www.gnu.org/software/octave> Further tutorials (by M Bosschaert) at <https://sites.google.com/a/uhasselt.be/maikel-bosschaert/home> (pdf files). -
13
library-brainmap
Brain Neuron Map
library-brainmap is a powerful library that enables you to create captivating Brain Neuron Maps, generate intricate mazes, and seamlessly integrate a user-friendly path-finding interface into your projects. Whether you're a developer, a researcher, or simply an enthusiast, this library opens up endless possibilities for representing and navigating complex systems. Features Brain Neuron Map Generation: Design visually striking neuron maps that emulate the intricate connections within a brain. ... -
14
Neuron
Future-proof note-taking and publishing based on Zettelkasten
Neuron is a Zettelkasten-based note-taking system and static site generator built in Haskell. It allows users to manage interlinked notes using plain-text Markdown files, which are automatically rendered into a web-based knowledge base. Neuron supports incremental builds, backlinks, and efficient navigation across linked content, making it ideal for personal knowledge management, digital gardens, and wikis. -
15
Ecco
Explain, analyze, and visualize NLP language models
Ecco is an interpretability tool for transformers that helps visualize and analyze how language models generate text, making model behavior more transparent. -
16
CNN Explainer
Learning Convolutional Neural Networks with Interactive Visualization
...Let’s break down a CNN into its basic building blocks. A tensor can be thought of as an n-dimensional matrix. In the CNN above, tensors will be 3-dimensional with the exception of the output layer. A neuron can be thought of as a function that takes in multiple inputs and yields a single output. The outputs of neurons are represented above as the red → blue activation maps. -
17
iqr is a simulation software to graphically design and control large-scale neuronal models. Simulations in iqr can control real-world devices in real-time. iqr can be extended by new neuron, and synapse types, and custom interfaces to hardware.
-
18
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. In that model each neuron in layer is connected to neurons in its surrounding in previous layer. -
19
Dynamic Routing Between Capsules
A PyTorch implementation of the NIPS 2017 paper
Dynamic Routing Between Capsules is a PyTorch implementation of the Capsule Network architecture originally proposed to address limitations in traditional convolutional neural networks. Capsule networks aim to improve how neural models represent spatial hierarchies and relationships between objects within images. Instead of scalar neuron activations, capsules output vectors that encode both the presence of features and their spatial properties such as orientation or pose. The repository implements the dynamic routing algorithm between capsules, which allows lower-level features to route their outputs to higher-level structures that best represent the detected patterns. ... -
20
NeuralSyns
NeuralSyns is a neural simulator for large spiking networks.
NeuralSyns is a neural simulator for large spiking networks. New neuron and synapse dynamics can be added, and complex network models can be easily built using the included tool NetBuilder. OpenGL is used to show the network's architecture and activity. -
21
CoAP On Lonworks
CoAP protocol for Neuron 6000 IC
CoAP-On-Lon is a very simple CoAP server protocol implementation from scratch, for Neuron 6000 Chips & Izot Router. See Code for the content. Lonworks, Neuron, Nodebuilder, Izot are trademarks of Echelon Corporation. -
22
A neuronal network simulator using NeuroML (as generated by neuroConstruct) for network description. Conductance- and rate-based Hodgkin-Huxley neuron models, and a number of other neurons & synapses. A 5-6-order RK method is used for integration.
-
23
MeCFES
Myoelectrically Controlled Functional Electrical Stimulation
The objective of this project is to develop and promote a method for restoring motor function lost due to upper motor neuron lesion (spinal cord injury, stroke) in a way that the user has direct control over the movement. When a muscle contracts it is causing a weak electrical signal that can be measured on the skin over the muscle- even if the muscle is almost completely paralysed (paretic). At the same time the muscle can be electrically stimulated to contract. -
24
-
25
NeuroGPS-Tree
A tool for recontructing neuron population automatically
