Zobrazeno 1 - 10
of 214
pro vyhledávání: '"Kiani, Narsis"'
Autor:
Ozelim, Luan, Uthamacumaran, Abicumaran, Abrahão, Felipe S., Hernández-Orozco, Santiago, Kiani, Narsis A., Tegnér, Jesper, Zenil, Hector
We give answer to an argument trying to show the divergence of Assembly Theory from LZ compression. We formally proved that any implementation of the concept of `copy number' underlying Assembly Theory (AT) and its assembly index (Ai) is equivalent t
Externí odkaz:
http://arxiv.org/abs/2408.15108
This paper studies the usefulness of incorporating path information in predicting chemical properties from molecular graphs, in the domain of QSAR (Quantitative Structure-Activity Relationship). Towards this, we developed a GNN-style model which can
Externí odkaz:
http://arxiv.org/abs/2407.14270
Autor:
Abrahão, Felipe S., Hernández-Orozco, Santiago, Kiani, Narsis A., Tegnér, Jesper, Zenil, Hector
We prove the full equivalence between Assembly Theory (AT) and Shannon Entropy via a method based upon the principles of statistical compression renamed `assembly index' that belongs to the LZ family of popular compression algorithms (ZIP, GZIP, JPEG
Externí odkaz:
http://arxiv.org/abs/2403.06629
Autor:
Radhakrishnan, Srijith, Yang, Chao-Han Huck, Khan, Sumeer Ahmad, Kumar, Rohit, Kiani, Narsis A., Gomez-Cabrero, David, Tegner, Jesper N.
We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate speech tr
Externí odkaz:
http://arxiv.org/abs/2310.06434
Autor:
Radhakrishnan, Srijith, Yang, Chao-Han Huck, Khan, Sumeer Ahmad, Kiani, Narsis A., Gomez-Cabrero, David, Tegner, Jesper N.
In this work, we explore Parameter-Efficient-Learning (PEL) techniques to repurpose a General-Purpose-Speech (GSM) model for Arabic dialect identification (ADI). Specifically, we investigate different setups to incorporate trainable features into a m
Externí odkaz:
http://arxiv.org/abs/2305.11244
Autor:
Munoz, Juan, Balsamy, Subash, Bernal-Tamayo, Juan P., Balubaid, Ali, de Infante, Alberto Maillo Ruiz, Lagani, Vincenzo, Gomez-Cabrero, David, Kiani, Narsis A., Tegner, Jesper
Discovering non-linear dynamical models from data is at the core of science. Recent progress hinges upon sparse regression of observables using extensive libraries of candidate functions. However, it remains challenging to model hidden non-observable
Externí odkaz:
http://arxiv.org/abs/2304.02443
Publikováno v:
npj Systems Biology and Applications, volume 10, number 82, year 2024
We demonstrate that the assembly pathway method underlying assembly theory (AT) is an encoding scheme widely used by popular statistical compression algorithms. We show that in all cases (synthetic or natural) AT performs similarly to other simple co
Externí odkaz:
http://arxiv.org/abs/2210.00901
Autor:
Balubaid, Ali, Alsolami, Samhan, Kiani, Narsis A., Gomez-Cabrero, David, Li, Mo, Tegner, Jesper
Publikováno v:
In iScience 15 November 2024 27(11)
Autor:
Zhang, Haoling, Yang, Chao-Han Huck, Zenil, Hector, Kiani, Narsis A., Shen, Yue, Tegner, Jesper N.
Publikováno v:
2020 IEEE Congress on Evolutionary Computation (CEC)
NeuroEvolution is one of the most competitive evolutionary learning frameworks for designing novel neural networks for use in specific tasks, such as logic circuit design and digital gaming. However, the application of benchmark methods such as the N
Externí odkaz:
http://arxiv.org/abs/2002.00539
Autor:
Hernández-Orozco, Santiago, Zenil, Hector, Riedel, Jürgen, Uccello, Adam, Kiani, Narsis A., Tegnér, Jesper
We show how complexity theory can be introduced in machine learning to help bring together apparently disparate areas of current research. We show that this new approach requires less training data and is more generalizable as it shows greater resili
Externí odkaz:
http://arxiv.org/abs/1910.02758