6 repository-uri
Awesome GitHub RepositoriesBackpropagation Implementations
Manual implementations of gradient-based optimization logic.
Explore 6 awesome GitHub repositories matching artificial intelligence & ml · Backpropagation Implementations. Refine with filters or upvote what's useful.
Awesome Backpropagation Implementations GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- rasbt/llms-from-scratch
rasbt/LLMs-from-scratch
97,260Vezi pe GitHubThis repository serves as an educational framework for building large language models from the ground up. It provides a structured curriculum that guides learners through the end-to-end lifecycle of model development, including data processing, architecture design, and optimization. By focusing on low-level implementation, the project enables users to master the fundamental mechanics of artificial intelligence without relying on high-level abstraction frameworks. The project distinguishes itself by constructing neural network components and gradient-based optimization logic from first princip
Implements gradient-based optimization logic manually to clarify the mechanics of weight updates and loss minimization.
Jupyter Notebookaiartificial-intelligencechatbot - karpathy/llm.c
karpathy/llm.c
30,230Vezi pe GitHubThis project is a low-dependency engine designed for training large language models using native C and CUDA. It provides a bare-metal environment for tensor computation, allowing for the execution of neural network operations directly on hardware accelerators without the overhead of high-level software abstractions. The framework distinguishes itself by implementing manual gradient backpropagation and custom hardware-specific kernels, providing granular control over memory mapping and computational precision. It supports distributed training across multiple graphics processors and compute nod
Calculates weight adjustments through explicit mathematical implementation rather than relying on automated differentiation engines.
Cuda - mnielsen/neural-networks-and-deep-learning
mnielsen/neural-networks-and-deep-learning
17,721Vezi pe GitHubThis project is a comprehensive educational resource and curriculum designed to teach the mathematical foundations and practical implementation of neural networks. It provides a structured path for understanding how computers learn from data, covering core concepts such as gradient descent, backpropagation, and the biological inspiration behind artificial neurons. The platform distinguishes itself by combining theoretical proofs with hands-on implementation exercises. It demonstrates the universal approximation theorem through visual explanations and guides users in building various architect
Implements backpropagation using matrix-based operations to update network weights.
Python - rasbt/deeplearning-models
rasbt/deeplearning-models
17,427Vezi pe GitHubThis repository is an educational collection of deep learning implementations designed to demonstrate the fundamental principles of neural network architecture and optimization. It provides a comprehensive resource for understanding machine learning through hands-on code examples, ranging from basic multilayer perceptrons to complex generative models. The project distinguishes itself by emphasizing the manual construction of models, including the implementation of backpropagation from scratch to illustrate core mathematical mechanics. It covers a wide array of architectural design patterns, s
Implements backpropagation from scratch to demonstrate the fundamental mathematical mechanics of neural network weight updates.
Jupyter Notebook - imagineailab/ai-by-hand-excel
ImagineAILab/ai-by-hand-excel
6,177Vezi pe GitHubAcest proiect constă în modele interactive bazate pe foi de calcul concepute pentru a demonstra mecanica matematică a backpropagation-ului, perceptronilor multistrat și atenției transformer. Servește ca simulator de rețea neuronală bazat pe Excel pentru calcularea manuală a operațiunilor tensoriale și a înmulțirilor de matrice pentru a vizualiza fluxul de date. Modelele oferă o modalitate de a vizualiza logica internă a rețelelor neuronale prin implementarea auto-atenției și a backpropagation-ului prin formule explicite de celule. Include exerciții matematice specifice pentru modelarea arhitecturii transformer și a straturilor perceptronilor multistrat. Simularea acoperă fundamentele deep learning-ului, inclusiv calculul trecerilor înainte (forward passes) și utilizarea gradient descent pentru actualizarea ponderilor. Utilizează simulări tensoriale bazate pe celule pentru a urmări actualizările parametrilor și a mapa relațiile ponderate în cadrul mecanismelor de atenție.
Implements gradient-based optimization logic through explicit formulas to demonstrate how weights are updated.
- oreilly-japan/deep-learning-from-scratch
oreilly-japan/deep-learning-from-scratch
4,791Vezi pe GitHubAcest proiect este o implementare educațională de deep learning și un tutorial de rețele neuronale în Python. Acesta oferă o colecție de implementări de rețele neuronale construite de la zero pentru a preda concepte fundamentale de deep learning fără utilizarea framework-urilor de nivel înalt. Materialul este livrat sub formă de cursuri în notebook-uri gestionate, prezentând exemple de cod interactive găzduite într-un mediu gestionat. Această abordare permite executarea exemplelor de implementare în cloud pentru a elimina nevoia de configurare a mașinii locale. Codul sursă acoperă implementarea modelelor de deep learning, arhitecturile rețelelor neuronale și fundamentele matematice ale machine learning-ului. Se concentrează pe dezvoltarea de nivel scăzut a modelelor AI pentru a demonstra modul în care datele circulă prin straturi și funcționarea internă a backpropagation-ului.
Implements manual gradient computation using the chain rule to demonstrate the mechanics of backpropagation.
Jupyter Notebook
