7 dépôts
Techniques for deferring model parameter creation until input data shapes are determined.
Distinguishing note: Focuses on lazy initialization for flexible network design.
Explore 7 awesome GitHub repositories matching artificial intelligence & ml · Dynamic Parameter Initialization. Refine with filters or upvote what's useful.
This project is a comprehensive Chinese translation of a technical deep learning textbook, providing an educational resource on the theory and implementation of neural networks. It functions as a collaborative technical translation project designed to make complex academic AI literature accessible to non-English speakers. The project utilizes a community-driven translation model that integrates external suggestions and pull requests to refine linguistic accuracy and reduce bias. It employs standardized terminology mapping to ensure a uniform vocabulary throughout the translated content. To i
Covers unsupervised methods for initializing convolution kernels.
This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex
Defers parameter allocation until the first data pass to allow flexible network definition.
This project is a browser-based machine learning education tool and neural network sandbox. It provides an interactive environment for experimenting with network architectures and hyperparameters to understand deep learning concepts. The tool functions as a visualizer for TensorFlow neural networks, allowing users to see how models learn and classify data in real time. It enables the prototyping of model architectures to observe how different hidden layers and neurons affect a network's ability to solve specific data patterns. The system covers neural network architecture and operation visua
Links UI sliders and inputs to hyperparameters to trigger immediate re-initialization of the network.
This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum
Provides instruction on using random distributions for weight initialization to break symmetry and improve model convergence.
This project provides a comprehensive technical guide and framework for engineering large-scale machine learning systems. It covers the full lifecycle of model development, focusing on the infrastructure and computational principles required to build, train, and serve generative AI models across distributed GPU clusters. The repository distinguishes itself by offering deep-dive tutorials and implementation strategies for complex system challenges. It emphasizes high-performance architectural primitives, such as collective communication orchestration, distributed tensor sharding, and static gr
Defers model parameter creation to CPU or virtual devices to optimize memory usage during startup.
This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen
Provides functions to set starting values for neural network parameters across submodules.
This project is a collection of structured study notes and notebooks serving as an educational resource for deep learning and neural network fundamentals. It provides a technical reference for implementing machine learning theory, covering everything from basic network design to the construction of advanced architectures. The material specifically focuses on the implementation of convolutional neural networks for computer vision and sequence models for natural language processing. It includes detailed guidance on building object detection systems, face recognition, and speech transcription mo
Provides strategies for random weight initialization to break symmetry and enable distinct feature learning.