metaqnn
Neural Network Architect Designer
Automatically designs convolutional neural network architectures using reinforcement learning and Q-learning algorithms
137 stars
7 watching
37 forks
Language: Python
last commit: over 7 years ago
Linked from 1 awesome list
Related projects:
Repository | Description | Stars |
---|---|---|
ahmedfgad/numpycnn | An implementation of a convolutional neural network (CNN) using NumPy for basic classification tasks. | 570 |
p-christ/nn_builder | Builds neural networks with less boilerplate code by providing a standardized interface for different architectures | 166 |
microsoft/archai | Automates the search for optimal neural network configurations in deep learning applications | 467 |
joeddav/devol | An evolutionary algorithm for designing neural networks in Keras | 950 |
molcik/python-neuron | A Python library for implementing and training various neural network architectures | 40 |
ahmedfgad/numpyann | An implementation of artificial neural networks using NumPy | 98 |
priba/nmp_qc | An implementation of neural networks on graph structures for learning molecular properties | 339 |
ramon-oliveira/aorun | A deep learning framework on top of PyTorch for building neural networks. | 61 |
mikecmpbll/rann | Provides objects and algorithms for designing, processing and training Artificial Neural Networks in Ruby. | 3 |
taolei87/rcnn | An implementation of neural network components and optimization methods for text analysis, including rationales for neural predictions. | 355 |
benedekrozemberczki/appnp | A PyTorch implementation of a graph neural network model that learns personalized node representations | 363 |
eliyaan/neuralnetworks-v-module | A V module to create and train multi-layer neural networks with customizable backpropagation | 19 |
ahmedfgad/cnngenetic | Trains convolutional neural networks using the genetic algorithm | 22 |
berkeleyautomation/gqcnn | Develops and analyzes convolutional neural networks for grasp quality in robotics | 313 |
codeplea/genann | A minimal C library for training and using feedforward artificial neural networks | 2,010 |