Publications

Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attention
Leo Schwinn
Doina Precup
Bjoern Eskofier
Dario Zanca
By and large, existing computational models of visual attention tacitly assume perfect vision and full access to the stimulus and thereby de… (voir plus)viate from foveated biological vision. Moreover, modeling top-down attention is generally reduced to the integration of semantic features without incorporating the signal of a high-level visual tasks that have been shown to partially guide human attention. We propose the Neural Visual Attention (NeVA) algorithm to generate visual scanpaths in a top-down manner. With our method, we explore the ability of neural networks on which we impose a biologically-inspired foveated vision constraint to generate human-like scanpaths without directly training for this objective. The loss of a neural network performing a downstream visual task (i.e., classification or reconstruction) flexibly provides top-down guidance to the scanpath. Extensive experiments show that our method outperforms state-of-the-art unsupervised human attention models in terms of similarity to human scanpaths. Additionally, the flexibility of the framework allows to quantitatively investigate the role of different tasks in the generated visual behaviors. Finally, we demonstrate the superiority of the approach in a novel experiment that investigates the utility of scanpaths in real-world applications, where imperfect viewing conditions are given.
2021-12-31
Trans. Mach. Learn. Res. (publié)
openreview.net
openreview.net
Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules
Yuhan Helena Liu
Arna Ghosh
Blake A. Richards
Eric Shea-Brown
Guillaume Lajoie
To unveil how the brain learns, ongoing work seeks biologically-plausible approximations of gradient descent algorithms for training recurre… (voir plus)nt neural networks (RNNs). Yet, beyond task accuracy, it is unclear if such learning rules converge to solutions that exhibit different levels of generalization than their nonbiologically-plausible counterparts. Leveraging results from deep learning theory based on loss landscape curvature, we ask: how do biologically-plausible gradient approximations affect generalization? We first demonstrate that state-of-the-art biologically-plausible learning rules for training RNNs exhibit worse and more variable generalization performance compared to their machine learning counterparts that follow the true gradient more closely. Next, we verify that such generalization performance is correlated significantly with loss landscape curvature, and we show that biologically-plausible learning rules tend to approach high-curvature regions in synaptic weight space. Using tools from dynamical systems, we derive theoretical arguments and present a theorem explaining this phenomenon. This predicts our numerical results, and explains why biologically-plausible rules lead to worse and more variable generalization properties. Finally, we suggest potential remedies that could be used by the brain to mitigate this effect. To our knowledge, our analysis is the first to identify the reason for this generalization gap between artificial and biologically-plausible learning rules, which can help guide future investigations into how the brain learns solutions that generalize.
2021-12-31
NeurIPS (publié)
doi.org
openreview.net
Biasly: a machine learning based platform for automatic racial discrimination detection in online texts
David Bamman
Chris Dyer
Noah A. Smith. 2014
Steven Bird
Ewan Klein
Edward Loper
Nat-527
Jacob Devlin
Ming-Wei Chang
Kenton Lee
Kristina Toutanova. 2019
Bert
Samuel Gehman
Suchin Gururangan
Maarten Sap
Dan Hendrycks
Kevin Gimpel. 2020
Gaussian
Alex Lamb
Di He … (voir 22 de plus)
Anirudh Goyal
Guolin Ke
Feng-Ju Liao
Mirco Ravanaelli
Yoshua Bengio
Zhenzhong Lan
Mingda Chen
Sebastian Goodman
Yann Lecun
Bernhard E. Boser
J. Denker
Don-608 nie Henderson
Robin Howard
Wayne Hubbard
Yinhan Liu
Myle Ott
Naman Goyal
Jingfei Du
Mandar Joshi
Danqi Chen
Omer Levy
Mike Lewis
Warning : this paper contains content that may 001 be offensive or upsetting. 002 Detecting hateful, toxic, and otherwise racist 003 or sexi… (voir plus)st language in user-generated online con-004 tents has become an increasingly important task 005 in recent years. Indeed, the anonymity, the 006 transience, the size of messages, and the dif-007 ficulty of management, facilitate the diffusion 008 of racist or hateful messages across the Inter-009 net. The critical influence of this cyber-racism 010 is no longer limited to social media, but also 011 has a significant effect on our society : corpo-012 rate business operation, users’ health, crimes, 013 etc. Traditional racist speech reporting chan-014 nels have proven inadequate due to the enor-015 mous explosion of information, so there is an 016 urgent need for a method to automatically and 017 promptly detect texts with racial discrimination. 018 We propose in this work, a machine learning-019 based approach to enable automatic detection 020 of racist text content over the internet. State-of-021 the-art machine learning models that are able 022 to grasp language structures are adapted in this 023 study. Our main contribution include 1) a large 024 scale racial discrimination data set collected 025 from three distinct sources and annotated ac-026 cording to a guideline developed by specialists, 027 2) a set of machine learning models with vari-028 ous architectures for racial discrimination de-029 tection, and 3) a web-browser-based software 030 that assist users to debias their texts when us-031 ing the internet. All these resources are made 032 publicly available.
2021-12-31
(publié)
www.semanticscholar.org
Bisimulation metrics and norms for real-weighted automata
Borja Balle
Pascale Gourdeau
Prakash Panangaden
2021-12-31
Information and Computation (publié)
doi.org
Brain-spinal cord interaction in long-term motor sequence learning in human: An fMRI study
Ali Khatibi
Shahabeddin Vahdat
Ovidiu Lungu
Jürgen Finsterbusch
Christian Büchel
Julien Cohen-Adad
Veronique Marchand-Pauvert
Julien Doyon
2021-12-31
NeuroImage (publié)
doi.org
Building Together - Towards a Roadmap for African Language Technologies
Kathleen Siminyu
Jade Abbott
Kọ́lá Túbọ̀sún
Aremu Anuoluwapo
Blessing Kudzaishe Sibanda
Kofi Yeboah
David Ifeoluwa Adelani
Masabata Mokgesi-Selinga
Frederick R. Apina
Angela Thandizwe Mthembu
Arshath Ramkilowan
Babatunde Oladimeji
2021-12-31
Social Science Research Network (publié)
doi.org
Catalyzing next-generation Artificial Intelligence through NeuroAI
Anthony Zador
Blake Aaron Richards
Bence Ölveczky
Sean Escola
Yoshua Bengio
Kwabena Boahen
Matthew Botvinick
Dmitri Chklovskii
Anne Churchland
Claudia Clopath
James DiCarlo
Surya Ganguli
Jeff Hawkins
Konrad Paul Kording
Alexei Koulakov
Yann Lecun
Timothy P Lillicrap
Adam Marblestone
Bruno Olshausen
Alexandre Pouget … (voir 7 de plus)
Cristina Savin
Terrence Sejnowski
Eero Simoncelli
Sara Solla
David Sussillo
Andreas S. Tolias
Doris Tsao
2021-12-31
arXiv.org (prépublication)
doi.org
arxiv.org
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
Eduard Gorbunov
Marina Danilova
David Dobre
Pavel Dvurechensky
Alexander Gasnikov
Gauthier Gidel
2021-12-31
Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (publié)
doi.org
openreview.net
Cognitive Models as Simulators: The Case of Moral Decision-Making
Ardavan S. Nobandegani
T. Shultz
Irina Rish
2021-12-31
CogSci (publié)
doi.org
arxiv.org
COIL: A Deep Architecture for Column Generation
Behrouz Babaki
Laurent Charlin
Sanjay Dominik Jena
. Column generation is a popular method to solve large-scale linear programs with an exponential number of variables. Several important appl… (voir plus)ications, such as the vehicle routing problem, rely on this technique in order to be solved. However, in practice, column generation methods suffer from slow convergence (i.e. they require too many iterations). Stabilization techniques, which carefully select the column to add at each iteration, are commonly used to improve convergence. In this work, we frame the problem of selecting which columns to add as one of sequential decision-making. We propose a neural column generation architecture that iteratively selects columns to be added to the problem. Our architecture is inspired by stabilization techniques and predicts the optimal duals, which are then used to select the columns to add. We proposed architecture, trained using imitation learning. Exemplified on the Vehicle Routing Problem, we show that several machine learning models yield good performance in predicting the optimal duals and that our architecture outperforms them as well as a popular state-of-the-art stabilization technique. Further, the architecture approach can generalize to instances larger than those observed during training.
2021-12-31
(publié)
www.semanticscholar.org
Combining Reinforcement Learning and Constraint Programming for Sequence-Generation Tasks with Hard Constraints
Daphne Lafleur
A. Chandar
Gilles Pesant
While Machine Learning (ML) techniques are good at generating data similar to a dataset, they lack the capacity to enforce constraints. On t… (voir plus)he other hand, any solution to a Constraint Programming (CP) model satisfies its constraints but has no obligation to imitate a dataset. Yet, we sometimes need both. In this paper we borrow RL-Tuner, a Reinforcement Learning (RL) algorithm introduced to tune neural networks, as our enabling architecture to exploit the respective strengths of ML and CP. RL-Tuner maximizes the sum of a pretrained network’s learned probabilities and of manually-tuned penalties for each violated constraint. We replace the latter with outputs of a CP model representing the marginal probabilities of each value and the number of constraint violations. As was the case for the original RL-Tuner, we apply our algorithm to music generation since it is a highly-constrained domain for which CP is especially suited. We show that combining ML and CP, as opposed to using them individually, allows the agent to reflect the pretrained network while taking into account constraints, leading to melodic lines that respect both the corpus’ style and the music theory constraints.
2021-12-31
International Conference on Principles and Practice of Constraint Programming (publié)
doi.org
Computing Nash Equilibria for Integer Programming Games
Margarida Carvalho
Andrea Lodi
João Pedro Pedroso
The recently defined class of integer programming games (IPG) models situations where multiple self-interested decision makers interact, wit… (voir plus)h their strategy sets represented by a finite set of linear constraints together with integer requirements. Many real-world problems can suitably be fit in this class, and hence anticipating IPG outcomes is of crucial value for policy makers and regulators. Nash equilibria have been widely accepted as the solution concept of a game. Consequently, their computation provides a reasonable prediction of the games outcome. In this paper, we start by showing the computational complexity of deciding the existence of a Nash equilibrium for an IPG. Then, using sufficient conditions for their existence, we develop two general algorithmic approaches that are guaranteed to approximate an equilibrium under mild conditions. We also showcase how our methodology can be changed to determine other equilibria definitions. The performance of our methods is analyzed through computational experiments in a knapsack game, a competitive lot-sizing game, and a kidney exchange game. To the best of our knowledge, this is the first time that equilibria computation methods for general integer programming games have been designed and computationally tested.
2021-12-31
European Journal of Operational Research (publié)
doi.org
arxiv.org