AlphaX-NASBench101
NAS Agent
An implementation of a Neural Architecture Search agent using Monte Carlo Tree Search and a predictive model for efficient search of neural network architectures on the NASBench-101 dataset.
Neural Architecture Search using Deep Neural Network and Monte Carlo Tree Search
167 stars
14 watching
23 forks
Language: Python
last commit: over 4 years ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
| Automates the search for optimal neural network configurations in deep learning applications | 468 |
| An implementation of a deep neural network architecture search method for mobile devices using the Caffe framework. | 52 |
| An implementation of Neural Architecture Search using Reinforcement Learning with a Controller RNN. | 433 |
| An OpenAI Gym environment for searching neural network architectures | 29 |
| An implementation of Neural Architecture Search Network models in Keras 2.0+, allowing for the creation and usage of NASNet architectures. | 199 |
| An autoML tool that searches and optimizes neural network architectures using tensorflow and keras. | 30 |
| An experimental method for efficiently searching neural network architectures using a single training run. | 489 |
| A toolbox to help understand neural networks' predictions by providing different analysis methods and a common interface. | 1,271 |
| Investigating neural networks for drug discovery using multiple chemical descriptors. | 3 |
| A PyTorch package implementing multi-task deep neural networks for natural language understanding | 2,238 |
| Provides an interface for building and evaluating neural process models for environmental prediction tasks using Python libraries. | 97 |
| Builds agents controlled by large language models (LLMs) to perform tasks with tool-based components | 940 |
| An implementation of a neural network architecture search algorithm optimized for mobile devices. | 271 |
| Automatically designs convolutional neural network architectures using reinforcement learning and Q-learning algorithms | 137 |
| A build system and framework for simulating multi-agent environments with fine-grained control | 6 |