21 citations · 73 across the 25 of their papers we have counts for
30 papers
A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Model
Srijith Radhakrishnan, Chao-Han Huck Yang, Sumeer Ahmad Khan +3
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 i…
IHCV: Discovery of Hidden Time-Dependent Control Variables in Non-Linear Dynamical Systems
Juan Munoz, Subash Balsamy, Juan P. Bernal-Tamayo +6
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 fun…
VLG-Net: Video-Language Graph Matching Network for Video Grounding
Mattia Soldan, Mengmeng Xu, Sisi Qu +2
Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands unde…
DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation
Jia-Hong Huang, Chao-Han Huck Yang, Fangyu Liu +9
In this work, we propose an AI-based method that intends to improve the conventional retinal disease treatment procedure and help ophthalmologists increase diagnosis efficiency and…
Learning Heat Diffusion for Network Alignment
Sisi Qu, Mengmeng Xu, Bernard Ghanem +1
Networks are abundant in the life sciences. Outstanding challenges include how to characterize similarities between networks, and in extension how to integrate information across n…
Evolving Neural Networks through a Reverse Encoding Tree
Haoling Zhang, Chao-Han Huck Yang, Hector Zenil +3
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 digit…
Interpretable Self-Attention Temporal Reasoning for Driving Behavior Understanding
Yi-Chieh Liu, Yung-An Hsieh, Min-Hung Chen +3
Performing driving behaviors based on causal reasoning is essential to ensure driving safety. In this work, we investigated how state-of-the-art 3D Convolutional Neural Networks (C…
Algorithmic Probability-guided Supervised Machine Learning on Non-differentiable Spaces
Santiago Hernández-Orozco, Hector Zenil, Jürgen Riedel +3
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 l…
Synthesizing New Retinal Symptom Images by Multiple Generative Models
Yi-Chieh Liu, Hao-Hsiang Yang, Chao-Han Huck Yang +5
Age-Related Macular Degeneration (AMD) is an asymptomatic retinal disease which may result in loss of vision. There is limited access to high-quality relevant retinal images and po…
Controllability, Multiplexing, and Transfer Learning in Networks using Evolutionary Learning
Rise Ooi, Chao-Han Huck Yang, Pin-Yu Chen +5
Networks are fundamental building blocks for representing data, and computations. Remarkable progress in learning in structurally defined (shallow or deep) networks has recently be…
Learning Functions in Large Networks requires Modularity and produces Multi-Agent Dynamics
C. H. Huck Yang, Rise Ooi, Tom Hiscock +2
Networks are abundant in biological systems. Small sized over-represented network motifs have been discovered, and it has been suggested that these constitute functional building b…
Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model
C. -H. Huck Yang, Fangyu Liu, Jia-Hong Huang +6
Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. Based on the fact that fun…
A Novel Hybrid Machine Learning Model for Auto-Classification of Retinal Diseases
C. -H. Huck Yang, Jia-Hong Huang, Fangyu Liu +5
Automatic clinical diagnosis of retinal diseases has emerged as a promising approach to facilitate discovery in areas with limited access to specialists. We propose a novel visual-…
The Thermodynamics of Network Coding, and an Algorithmic Refinement of the Principle of Maximum Entropy
Hector Zenil, Narsis A. Kiani, Jesper Tegnér
The principle of maximum entropy (Maxent) is often used to obtain prior probability distributions as a method to obtain a Gibbs measure under some restriction giving the probabilit…
Algorithmic Complexity and Reprogrammability of Chemical Structure Networks
Hector Zenil, Narsis A. Kiani, Ming-Mei Shang +1
Here we address the challenge of profiling causal properties and tracking the transformation of chemical compounds from an algorithmic perspective. We explore the potential of appl…
Symmetry and Algorithmic Complexity of Polyominoes and Polyhedral Graphs
Hector Zenil, Narsis A. Kiani, Jesper Tegnér
We introduce a definition of algorithmic symmetry able to capture essential aspects of geometric symmetry. We review, study and apply a method for approximating the algorithmic com…
Algorithmic Causal Deconvolution of Intertwined Programs and Networks by Generative Mechanism
Hector Zenil, Narsis A. Kiani, Allan A. Zea +1
Complex data usually results from the interaction of objects produced by different generating mechanisms. Here we introduce a universal, unsupervised and parameter-free model-orien…
Algorithmic Information Dynamics of Persistent Patterns and Colliding Particles in the Game of Life
Hector Zenil, Narsis A. Kiani, Jesper Tegnér
Without loss of generalisation to other systems, including possibly non-deterministic ones, we demonstrate the application of methods drawn from algorithmic information dynamics to…
Predictive Systems Toxicology
Narsis A. Kiani, Ming-Mei Shang, Hector Zenil +1
In this review we address to what extent computational techniques can augment our ability to predict toxicity. The first section provides a brief history of empirical observations…
An Algorithmic Information Calculus for Causal Discovery and Reprogramming Systems
Hector Zenil, Narsis A. Kiani, Francesco Marabita +5
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-th…
HiDi: An efficient reverse engineering schema for large scale dynamic regulatory network reconstruction using adaptive differentiation
Yue Deng, Hector Zenil, Jesper Tégner +1
The use of differential equations (ODE) is one of the most promising approaches to network inference. The success of ODE-based approaches has, however, been limited, due to the dif…
Characterization and reduction of variability in selection based on effect-size using association measures in cohort study of heterogeneous diseases
Venkateshan Kannan, Kristina Alexandersson, Jesper Tegner
Cohort studies employ pairwise measures of association to quantify dependencies among conditions and exposures. To reliably use these measures to draw conclusions about the underly…
Evaluating Network Inference Methods in Terms of Their Ability to Preserve the Topology and Complexity of Genetic Networks
Narsis A. Kiani, Hector Zenil, Jakub Olczak +1
Network inference is a rapidly advancing field, with new methods being proposed on a regular basis. Understanding the advantages and limitations of different network inference meth…
Approximations of Algorithmic and Structural Complexity Validate Cognitive-behavioural Experimental Results
Hector Zenil, James A. R. Marshall, Jesper Tegnér
Being able to objectively characterise the intrinsic complexity of behavioural patterns resulting from human or animal decisions is fundamental for deconvolving cognition and desig…