Search Results for "cortex-m"
Sort By:
20 projects for "cortex-m" with 2 filters applied:
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
1
Machine Learning Systems
Introduction to Machine Learning Systems
Machine Learning Systems is an open educational repository that serves as the source and learning stack for the Machine Learning Systems textbook, a project focused on teaching how to engineer AI systems that work reliably in real-world environments. Rather than concentrating only on model training, the material emphasizes the broader discipline of AI engineering, covering efficiency, reliability, deployment, and evaluation across the full lifecycle of intelligent systems. The repository... -
2
TurboFieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
TurboFieldfare is a custom Swift and Metal runtime for running the instruction-tuned Gemma 4 26B-A4B model on Apple Silicon Macs with limited memory. Instead of loading the entire model, it keeps the shared core and KV cache in RAM while streaming only the routed experts required for each token from SSD. This approach reduces active memory use to roughly 2 GB while the installed model occupies about 14.3 GB of storage. The project includes a native Mac application, command-line tools, a... -
3
uzu
A high-performance inference engine for AI models
...Written primarily in Rust and leveraging Apple’s Metal framework, the project focuses on maximizing performance when executing large language models and other AI workloads on devices such as Mac computers with M-series chips. The engine implements a hybrid architecture in which model layers can be executed either as custom GPU kernels or through Apple’s MPSGraph API, allowing it to balance performance and compatibility depending on the workload. By utilizing Apple’s unified memory architecture, uzu reduces memory copying overhead and improves inference throughput for local AI workloads. ... -
4
MLX Engine
LM Studio Apple MLX engine
...Built on top of the mlx-lm and mlx-vlm ecosystems, the engine provides a unified architecture capable of supporting both text-only and multimodal models. Its design focuses on high-performance on-device inference, leveraging Apple’s MLX stack to accelerate computation on M-series chips. The project introduces modular VisionAddOn components that allow image embeddings to be integrated seamlessly into language model workflows. It is bundled with newer versions of LM Studio but can also be used independently for experimentation and development. Overall, mlx-engine serves as a specialized high-efficiency runtime for local AI workloads on macOS systems. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
cortex
Production infrastructure for machine learning at scale
Cortex is an open-source platform designed for building, deploying, and managing machine learning applications in production environments. The framework provides infrastructure tools that allow developers to transform trained machine learning models into scalable web services. Cortex handles many operational challenges associated with deploying AI systems, such as managing dependencies, orchestrating data pipelines, and scaling services under load. -
6
uTensor
TinyML AI inference library
...This approach allows developers to build machine learning models using standard frameworks and then deploy them to devices with extremely limited memory and processing power. The runtime library is intentionally lightweight and optimized for platforms such as Arm Cortex-M microcontrollers, making it suitable for real-time edge applications. -
7
Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
...The repository is structured as a full training pipeline: dataset preparation, preprocessing into spectrograms, Tacotron training, WaveNet (or Griffin-Lim) vocoder training, and final waveform synthesis. It includes directory layouts and logging directories for multiple datasets such as LJSpeech and M-AILABS en_US/en_UK, making it easier to adapt to new English corpora. Separate log trees track mel-spectrograms, attention plots, evaluation audio, and vocoder outputs, so you can inspect how alignment and audio quality evolve over time. -
8
SLEF
Subjective Logic Experimental Framework
Experiment developed for the paper Subjective Logic Operators in Trust Assessment: An Empirical Study by F. Cerutti, L. M. Kaplan, T. J. Norman, N. Oren, and A. Toniolo ISF Journal, 2014 -
9
dnrDALMAS
A general-level Prolog implementation of the DALMAS architecture.
...A DALMAS is regulated by a normative system based on an algebraic version of the theory of normative positions. For more information about dnrDALMAS, see the following technical report: Hjelmblom, M. (2008). Deontic action-logic multi-agent systems in Prolog. University of Gävle, Division of Computer Science; University of Gävle. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-1475 See also: Odelstad, J., & Boman, M. (2004). Algebras for Agent Norm-Regulation. Annals of Mathematics and Artificial Intelligence, 42(1), 141–166. http://doi.org/10.1023/B:AMAI.0000034525.49481.4a -
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
10
jDALMAS
A Java front-end to the dnrDALMAS Prolog Module.
A Java front-end to the dnrDALMAS Prolog Module, as described in the following paper: Hjelmblom, M., & Odelstad, J. (2009). jDALMAS: A Java/Prolog Framework for Deontic Action-Logic Multi-Agent Systems. In A. Håkansson, N. Nguyen, R. Hartung, R. Howlett, & L. Jain (Eds.), Agent and Multi-Agent Systems: Technologies and Applications (Vol. 5559, pp. 110–119). Berlin / Heidelberg: Springer. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-3963 -
11
This site contains four packages of Mass and mass-based density estimation. 1. The first package is about the basic mass estimation (including one-dimensional mass estimation and Half-Space Tree based multi-dimensional mass estimation). This packages contains the necessary codes to run on MATLAB. 2. The second package includes source and object files of DEMass-DBSCAN to be used with the WEKA system. 3. The third package DEMassBayes includes the source and object files of a Bayesian...
-
12
nn22 Basic Neural Networks for Octave
Simple .m files, Basic Neural Networks study for Octave (or Matlab)
--> For a more detailed description check the README text under the 'Files' menu option :) The project consists of a few very simple .m files for a Basic Neural Networks study under Octave (or Matlab). The idea is to provide a context for beginners that will allow to develop neural networks, while at the same time get to see and feel the behavior of a basic neural networks' functioning. The code is completely open to be modified and may suit several scenarios. ... -
13
gannu
Java API and tools for performing NLP and other AI tasks
...V., Gelbukh, A. F. & Sidorov, G. (2013). Simple Window Selection Strategies for the Simplified Lesk Algorithm for Word Sense Disambiguation.. In F. Castro, A. F. Gelbukh & M. González (eds.), MICAI (1) (pp. 217-227), : Springer. ISBN: 978-3-642-45113-3 The zip file contains Gannu jar, source, API documentation and necessary resources for performing research. Gannu uses the following projects: Weka, JExcel API, Stanford POS Tagger and WordNet. Please cite them when using Gannu. -
14
Black Hole Cortex
Sphere surface layers of visual cortex approach maximum info density
...We can think of Wikipedia as a layer above our brains, a global SphereSurface of large surface area (a cortex layered on billions of minds) and small (10000 most important pages) density. -
15
Dinapter:
Generate adaptation contracts between incompatible services
...Dinapter: Automatic Adapter Specification for Software Composition, PROLE'08, ENTCS, 2008 - http://goo.gl/VrQvG ...and later integrated and improved within the ITACA toolbox (http://itaca.gisum.uma.es/): * J. Camara, J.A. Martín, G. Salaun, J. Cubo, M. Ouederni, C. Canal, E. Pimentel. ITACA: An integrated toolbox for the automatic composition and adaptation of Web services, ICSE'09, 2009 - http://goo.gl/oFGe8 -
16
BayesianCortex
simple algorithm for a realtime interactive visual cortex for painting
A paint program where the canvas is the visual cortex of a simple kind of artificial intelligence. You paint with the mouse into its dreams and it responds by changing what you painted gradually. There will also be an API for using it with other programs as a general high-dimensional space. Each pixel's brightness is its own dimension. Bayesian nodes have exactly 3 childs because that is all thats needed to do NAND in a fuzzy way as Bayes' Rule which is NAND at certain extremes. ... -
17
Mito-MAS-m is a simulator of the mitochondrial inner membrane and the enzymatic complexes embedded in it, implementing a coarse-grained (CG) model of the molecules using rigid structures and Dissipative Particules Dynamics (DPD) as motion equation.
-
18
Random Forest classification implementation in Java based on Breiman's algorithm (2001). It assumes the data is in the form [ X_1, X_2, . . ., X_M, Y ] where Y \in {0, 1, . . ., C}. The user must define M, C, and m initially.
-
19
An AI simulation patterned on the design suggested in the book, 'Growing Artificial Societies' by J M Epstein & R Axtell I hope to use this s/w for some intermediate/advanced experiments into economic, social & political studies of mass psychology.
-
20
Laguna M.1
Flagship Poolside model for agentic coding and software engineering
Laguna M.1 is Poolside’s flagship Mixture-of-Experts model built specifically for agentic coding, software engineering, and long-horizon autonomous workflows. It contains approximately 225.8B total parameters with 23.4B activated per token, making it substantially larger and more capable than Laguna XS.2 while maintaining efficient inference through sparse activation.
- Previous
- You're on page 1
- Next
