no code implementations • 23 Dec 2023 • Weijie Xiong, Giorgio Facelli, Mehrad Sahebi, Owen Agnel, Thiparat Chotibut, Supanut Thanasilp, Zoë Holmes
Notably, the expressivity of QELMs is fundamentally limited by the number of Fourier frequencies and the number of observables, while the complexity of the prediction hinges on the reservoir.
no code implementations • 28 Aug 2023 • Apimuk Sornsaeng, Ninnat Dangniam, Thiparat Chotibut
This is in contrast to the conventional application of reservoir computing that concentrates on the prediction of the dynamics of observables.
no code implementations • 4 Aug 2023 • Teerachote Pakornchote, Natthaphon Choomphon-anomakhun, Sorrjit Arrerut, Chayanon Atthapak, Sakarn Khamkaeo, Thiparat Chotibut, Thiti Bovornratanaraks
The energy differences between these structures and the true ground states are, on average, 68. 1 meV/atom lower than those generated by the original CDVAE.
1 code implementation • 22 Jun 2023 • Teerachote Pakornchote, Annop Ektarawong, Thiparat Chotibut
Accurately predicting the elastic properties of crystalline solids is vital for computational materials science.
no code implementations • 16 Dec 2021 • Jirawat Tangpanitanon, Chanatip Mangkang, Pradeep Bhadola, Yuichiro Minato, Dimitris G. Angelakis, Thiparat Chotibut
Despite empirical successes of recurrent neural networks (RNNs) in natural language processing (NLP), theoretical understanding of RNNs is still limited due to intrinsically complex non-linear computations.
no code implementations • 14 Jun 2021 • Apimuk Sornsaeng, Ninnat Dangniam, Pantita Palittapongarnpim, Thiparat Chotibut
Inspired by random walk on graphs, diffusion map (DM) is a class of unsupervised machine learning that offers automatic identification of low-dimensional data structure hidden in a high-dimensional dataset.
no code implementations • 16 Feb 2021 • Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Grzegorz Kosiorowski, Michał Misiurewicz, Georgios Piliouras
We establish that, even in simple linear non-atomic congestion games with two parallel links and any fixed learning rate, unless the game is fully symmetric, increasing the population size or the scale of costs causes learning dynamics to become unstable and eventually chaotic, in the sense of Li-Yorke and positive topological entropy.
no code implementations • 25 Nov 2019 • Zuozhu Liu, Thiparat Chotibut, Christopher Hillar, Shaowei Lin
Motivated by the celebrated discrete-time model of nervous activity outlined by McCulloch and Pitts in 1943, we propose a novel continuous-time model, the McCulloch-Pitts network (MPN), for sequence learning in spiking neural networks.
2 code implementations • 22 May 2018 • Mirco Milletarí, Thiparat Chotibut, Paolo E. Trevisanutto
We present a Statistical Mechanics (SM) model of deep neural networks, connecting the energy-based and the feed forward networks (FFN) approach.