17 papers · ranked by Valyu relevance
Yunxuan Dong, Siyuan Chen, Jisen Zhang
Genotype-to-Phenotype (G2P) prediction plays a pivotal role in crop breeding, enabling the identification of superior genotypes based on genomic data. Rice (Oryza sativa), one of the most important staple crops, faces challenges in improving yield and resilience due to the complex genetic architecture of agronomic…
Farhana Hossain Swarnali, Miaomiao Zhang, Tonmoy Hossain
Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the highdimensional data space, where group actions apply uniformly across the entire input, making it…
Robin Quessard, Thomas D. Barrett, William R. Clements
Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of symmetry preserving transformations. Inspired by this formalism, we propose a…
Yusuke Mukuta, Tatsuya Harada
This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with the transformations on the input. Therefore, it is important to construct pretext tasks for…
Putri A. van der Linden, Alejandro García-Castellanos, Sharvaree Vadgama, Thijs P. Kuipers + 1 more
'Sharvaree Vadgama' 'Thijs P. Kuipers' 'Erik J. Bekkers'] Group equivariance has emerged as a valuable inductive bias in deep learning, enhancing generalization, data efficiency, and robustness. Classically, group equivariant methods require the groups of interest to be known beforehand, which may not be realistic for…
Jake L. Amey, Jake Keeley, Tajwar Choudhury, Ilya Kuprov
Title: Significance Artificial neural networks are famously opaque-it is often unclear how they work. In this communication, we propose a group-theoretical way of finding out. It reveals considerable internal sophistication, even in simple neural networks: our nets apparently invented an elegant digital filter, a…
Elena Celledoni, Matthias J Ehrhardt, Christian Etmann, Brynjulf Owren + 2 more
'Brynjulf Owren' 'Carola-Bibiane Schönlieb' 'Ferdia Sherry'] Title: Abstract In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into…
Jaemyung Yu, Jaehyun Choi, Dong-Jae Lee, Ha Hong + 1 more
Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant representations, embedding semantically the same inputs despite transformations.…
Gian Marco Visani, Michael N. Pun, Armita Nourmohammad
Group-equivariant neural networks have emerged as a data-efficient approach to solve classification and regression tasks, while respecting the relevant symmetries of the data. However, little work has been done to extend this paradigm to the unsupervised and generative domains. Here, we present Holographic-(V)AE…
Joel Z. Leibo, Qianli Liao, Fabio Anselmi, Tomaso Poggio + 1 more
Is visual cortex made up of general-purpose information processing machinery, or does it consist of a collection of specialized modules? If prior knowledge, acquired from learning a set of objects is only transferable to new objects that share properties with the old, then the recognition system’s optimal organization…
Gian Marco Visani, Michael N. Pun, Arman Angaji, Armita Nourmohammad
Group-equivariant neural networks have emerged as an efficient approach to model complex data, using generalized convolutions that respect the relevant symmetries of a system. These techniques have made advances in both the supervised learning tasks for classification and regression, and the unsupervised tasks to…
Alex Gabel, Rick Quax, Efstratios Gavves
Understanding symmetries within data is crucial for explainability and enhancing model efficiency in artificial intelligence. This work investigates an approach to neural symmetry detection, specifically leveraging the mathematical framework of Lie theory. Our approach projects data into a low-dimensional latent space…
Irina Higgins, Sébastien Racanière, Danilo Rezende
Biological intelligence is remarkable in its ability to produce complex behavior in many diverse situations through data efficient, generalizable, and transferable skill acquisition. It is believed that learning “good” sensory representations is important for enabling this, however there is little agreement as to what…
Vincent Mallet, Jean-Philippe Vert
As DNA sequencing technologies keep improving in scale and cost, there is a growing need to develop machine learning models to analyze DNA sequences, e.g., to decipher regulatory signals from DNA fragments bound by a particular protein of interest. As a double helix made of two complementary strands, a DNA fragment can…
Terence Broad, Frederic Fol Leymarie, Mick Grierson, Tiago Martins + 2 more
This paper presents the network bending framework, a new approach for manipulating and interacting with deep generative models. We present a comprehensive set of deterministic transformations that can be inserted as distinct layers into the computational graph of a trained generative neural network and applied during…
Vladimír Kunc, Jiří Kléma
Gene expression profiling was made cheaper by the NIH LINCS program that profiles only ~1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D–GEX method employs neural networks to infer the whole profile. However, the original D–GEX can be further significantly improved. We have analyzed…
Emma Tysinger, Brajesh Rai, Anton Sinitskiy
Meaningful exploration of the chemical space of druglike molecules in drug design is a highly challenging task due to a combinatorial explosion of possible modifications of molecules. In this work, we address this problem with transformer models, a type of machine learning (ML) model, with recent demonstrated success…