rnn_adversarial_reprogramming
AI summary
Neural network reprogramming
Repurposes pre-trained neural networks for new classification tasks through adversarial reprogramming of their inputs.
- stars
- 6
- forks
- 5
- watching
- 5
Similar projects
Found by comparing what the projects do, not just their names.
Network reprogramming
This project enables reprogramming of pre-trained neural networks to work on new tasks by fine-tuning them on smaller datasets.
Model reprogramming
Cross-modal Adversarial Reprogramming enables retraining of image models on text classification tasks
Robust network trainer
Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques.
NLP Task Adaptation
An approach to transfer learning for NLP tasks using adversarial reprogramming and word-level task-specific embeddings.
Speech Recognition
Developing low-resource speech command recognition systems using adversarial reprogramming and transfer learning
Neural network optimizer
Trains artificial neural networks using the genetic algorithm
Neural network library
An implementation of artificial neural networks using NumPy
RNN processor
A deep learning implementation of a VRNN model for sequential data processing
Neural net architecture
An implementation of a PyTorch-based neural network architecture for image classification tasks.
Neural network builder
A deep learning framework on top of PyTorch for building neural networks.
Language model
An implementation of DeepMind's Relational Recurrent Neural Networks (Santoro et al. 2018) in PyTorch for word language modeling
Neural network
A small neural network implementation of the backpropagation algorithm in Haskell
RNN demonstrator
A demonstration project of a recurrent neural network implemented with Theano
Adversarial Visualizer
An online tool allowing users to visualize and generate adversarial examples to deceive neural networks
CNN Trainer
Trains CNNs using a genetic algorithm for classification problems where one class per sample is allowed.
