Search Results for author: Mohammadamin Tavakoli

Found 8 papers, 0 papers with code

Unraveling the Molecular Magic: AI Insights on the Formation of Extraordinarily Stretchable Hydrogels

no code implementations8 Mar 2024 Shahriar Hojjati Emmami, Ali Pilehvar Meibody, Lobat Tayebi, Mohammadamin Tavakoli, Pierre Baldi

The deliberate manipulation of ammonium persulfate, methylenebisacrylamide, dimethyleacrylamide, and polyethylene oxide concentrations resulted in the development of a hydrogel with an exceptional stretchability, capable of extending up to 260 times its original length.

Deep Learning Models of the Discrete Component of the Galactic Interstellar Gamma-Ray Emission

no code implementations6 Jun 2022 Alexander Shmakov, Mohammadamin Tavakoli, Pierre Baldi, Christopher M. Karwin, Alex Broughton, Simona Murgia

A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky.

Rxn Hypergraph: a Hypergraph Attention Model for Chemical Reaction Representation

no code implementations2 Jan 2022 Mohammadamin Tavakoli, Alexander Shmakov, Francesco Ceccarelli, Pierre Baldi

To achieve such skills, it is important to develop good representations of chemical reactions, or good deep learning architectures that can learn such representations automatically from the data.

Property Prediction

Tourbillon: a Physically Plausible Neural Architecture

no code implementations13 Jul 2021 Mohammadamin Tavakoli, Peter Sadowski, Pierre Baldi

The circular autoencoders are trained in self-supervised mode by recirculation algorithms and the top layer in supervised mode by stochastic gradient descent, with the option of propagating error information through the entire stack using non-symmetric connections.

SPLASH: Learnable Activation Functions for Improving Accuracy and Adversarial Robustness

no code implementations16 Jun 2020 Mohammadamin Tavakoli, Forest Agostinelli, Pierre Baldi

Furthermore, we show that SPLASH units significantly increase the robustness of deep neural networks to adversarial attacks.

Adversarial Robustness

Continuous Representation of Molecules Using Graph Variational Autoencoder

no code implementations17 Apr 2020 Mohammadamin Tavakoli, Pierre Baldi

In order to continuously represent molecules, we propose a generative model in the form of a VAE which is operating on the 2D-graph structure of molecules.

Decoder Property Prediction

Symmetric-APL Activations: Training Insights and Robustness to Adversarial Attacks

no code implementations25 Sep 2019 Mohammadamin Tavakoli, Forest Agostinelli, Pierre Baldi

Finally, we show that the use of Symmetric-APL activations can significantly increase the robustness of deep neural networks to adversarial attacks.

Cannot find the paper you are looking for? You can Submit a new open access paper.