tuomaso

Label-free-CBM

A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

train_mnist_fast

How to train a CNN to 99% accuracy on MNIST in less than a second on a laptop

CLIP-dissect

An automatic and efficient tool to describe functionalities of individual neurons in DNNs

radial_rl_v2

This repository contains the official code for our NeurIPS 2021 publication "Robust Deep Reinforcement Learning through Adversarial Loss​"

Linear-Explanations

Efficient-LLM-automated-interpretability

radial_rl

Code used in our paper "Robust Deep Reinforment Learning through Adversarial Loss"

SC2LE-implementation

An implementation of the fully convolutional agent for playing minigames in the Starcraft 2 learning environment introduced in https://arxiv.org/abs/1708.04782.

efficient_net

Modifying the efficientnet implementation from https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet to make it run locally on a given dataset.

automated-interpretability-tuning

Testing prompt tuning methods to improve explanation quality.

tuomaso/train_mnist_fast

How to train a CNN to 99% accuracy on MNIST in less than a second on a laptop

tuomaso/tuomaso.github.io

personal website

tuomaso/radial_rl

Code used in our paper "Robust Deep Reinforment Learning through Adversarial Loss"

tuomaso/automated-interpretability-tuning

Testing prompt tuning methods to improve explanation quality.

tuomaso/radial_rl_v2

This repository contains the official code for our NeurIPS 2021 publication "Robust Deep Reinforcement Learning through Adversarial Loss​"

tuomaso/efficient_net

Modifying the efficientnet implementation from https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet to make it run locally on a given dataset.

tuomaso/SC2LE-implementation

An implementation of the fully convolutional agent for playing minigames in the Starcraft 2 learning environment introduced in https://arxiv.org/abs/1708.04782.