1 code implementation • bioRxiv 2023 • Abdel Rahman Alsabbagh, Alberto Maillo Ruiz de Infante, David Gomez-Cabrero, Narsis A. Kiani, Sumeer Ahmad Khan, Jesper N. Tegnér
We benchmark three foundation models, scGPT, scBERT, and Geneformer, using skewed single-cell cell-type distribution for cell-type annotation.
1 code implementation • 10 Oct 2023 • Srijith Radhakrishnan, Chao-Han Huck Yang, Sumeer Ahmad Khan, Rohit Kumar, Narsis A. Kiani, David Gomez-Cabrero, Jesper N. Tegner
We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 18 May 2023 • Srijith Radhakrishnan, Chao-Han Huck Yang, Sumeer Ahmad Khan, Narsis A. Kiani, David Gomez-Cabrero, Jesper N. Tegner
In this work, we explore Parameter-Efficient-Learning (PEL) techniques to repurpose a General-Purpose-Speech (GSM) model for Arabic dialect identification (ADI).
1 code implementation • 5 Apr 2023 • Juan Munoz, Subash Balsamy, Juan P. Bernal-Tamayo, Ali Balubaid, Alberto Maillo Ruiz de Infante, Vincenzo Lagani, David Gomez-Cabrero, Narsis A. Kiani, Jesper Tegner
However, it remains challenging to model hidden non-observable control variables governing switching between different dynamical regimes.
1 code implementation • ICLR 2023 • Anuj Daga, Sumeer Ahmad Khan, David Gomez Cabrero, Robert Hoehndorf, Narsis A. Kiani, Jesper Tegnér
The LEP-AD model scales favorably in performance with the size of training data.
Ranked #1 on Protein Language Model on DAVIS-DTA
1 code implementation • 3 Feb 2020 • Haoling Zhang, Chao-Han Huck Yang, Hector Zenil, Narsis A. Kiani, Yue Shen, Jesper N. Tegner
Using RET, two types of approaches -- NEAT with Binary search encoding (Bi-NEAT) and NEAT with Golden-Section search encoding (GS-NEAT) -- have been designed to solve problems in benchmark continuous learning environments such as logic gates, Cartpole, and Lunar Lander, and tested against classical NEAT and FS-NEAT as baselines.
no code implementations • 7 Oct 2019 • Santiago Hernández-Orozco, Hector Zenil, Jürgen Riedel, Adam Uccello, Narsis A. Kiani, Jesper Tegnér
We show how complexity theory can be introduced in machine learning to help bring together apparently disparate areas of current research.
no code implementations • 18 Feb 2018 • Hector Zenil, Narsis A. Kiani, Allan A. Zea, Jesper Tegnér
Complex data usually results from the interaction of objects produced by different generating mechanisms.
2 code implementations • 16 Feb 2018 • Hector Zenil, Narsis A. Kiani, Antonio Rueda-Toicen, Allan A. Zea, Jesper Tegnér
We introduce a family of unsupervised, domain-free, and (asymptotically) model-independent algorithms based on the principles of algorithmic probability and information theory designed to minimize the loss of algorithmic information, including a lossless-compression-based lossy compression algorithm.
Data Structures and Algorithms Information Theory Information Theory Physics and Society
no code implementations • 15 Sep 2017 • Hector Zenil, Narsis A. Kiani, Francesco Marabita, Yue Deng, Szabolcs Elias, Angelika Schmidt, Gordon Ball, Jesper Tegnér
We demonstrate that the algorithmic information content of a system is deeply connected to its potential dynamics, thus affording an avenue for moving systems in the information-theoretic space and controlling them in the phase space.
no code implementations • 1 Sep 2017 • Santiago Hernández-Orozco, Narsis A. Kiani, Hector Zenil
The natural approach introduced here appears to be a better approximation to biological evolution than models based exclusively upon random uniform mutations, and it also approaches a formal version of open-ended evolution based on previous formal results.
3 code implementations • 1 Sep 2016 • Hector Zenil, Santiago Hernández-Orozco, Narsis A. Kiani, Fernando Soler-Toscano, Antonio Rueda-Toicen
We also test the measure on larger objects including dual, isomorphic and cospectral graphs for which we know that algorithmic randomness is low.
Information Theory Computational Complexity Information Theory H.1.1