Publications

In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators
Dmytro Humeniuk
Houssem Ben Braiek
Thomas Reid
Foutse Khomh
2024-10-26
Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (published)
doi.org
arxiv.org
Brain-like learning with exponentiated gradients
Jonathan Cornford
Roman Pogodin
Arna Ghosh
Kaiwen Sheng
Brendan A. Bicknell
Olivier Codol
Beverley A. Clark
Guillaume Lajoie
Blake A. Richards
Computational neuroscience relies on gradient descent (GD) for training artificial neural network (ANN) models of the brain. The advantage o… (see more)f GD is that it is effective at learning difficult tasks. However, it produces ANNs that are a poor phenomenological fit to biology, making them less relevant as models of the brain. Specifically, it violates Dale’s law, by allowing synapses to change from excitatory to inhibitory, and leads to synaptic weights that are not log-normally distributed, contradicting experimental data. Here, starting from first principles of optimisation theory, we present an alternative learning algorithm, exponentiated gradient (EG), that respects Dale’s Law and produces log-normal weights, without losing the power of learning with gradients. We also show that in biologically relevant settings EG outperforms GD, including learning from sparsely relevant signals and dealing with synaptic pruning. Altogether, our results show that EG is a superior learning algorithm for modelling the brain with ANNs.
2024-10-25
bioRxiv (preprint)
doi.org
Efficient Biological Data Acquisition through Inference Set Design
Ihor Neporozhnii
Julien Roy
Emmanuel Bengio
Jason Hartford
In drug discovery, highly automated high-throughput laboratories are used to screen a large number of compounds in search of effective drugs… (see more). These experiments are expensive, so one might hope to reduce their cost by only experimenting on a subset of the compounds, and predicting the outcomes of the remaining experiments. In this work, we model this scenario as a sequential subset selection problem: we aim to select the smallest set of candidates in order to achieve some desired level of accuracy for the system as a whole. Our key observation is that, if there is heterogeneity in the difficulty of the prediction problem across the input space, selectively obtaining the labels for the hardest examples in the acquisition pool will leave only the relatively easy examples to remain in the inference set, leading to better overall system performance. We call this mechanism inference set design, and propose the use of a confidence-based active learning solution to prune out these challenging examples. Our algorithm includes an explicit stopping criterion that interrupts the acquisition loop when it is sufficiently confident that the system has reached the target performance. Our empirical studies on image and molecular datasets, as well as a real-world large-scale biological assay, show that active learning for inference set design leads to significant reduction in experimental cost while retaining high system performance.
2024-10-24
ArXiv (preprint)
doi.org
arxiv.org
Investigating Alpha-DaRT Source Daughter Diffusion in Intra-Rectal Animal Models
Mélodie Cyr
Behnaz Behmand
Naim Chabaytah
Joud Babik
Mirta Dumancic
Joanna Li
Guillaume St-Jean
Shirin A. Enger
2024-10-24
Brachytherapy (published)
doi.org
Prediction of Final Phosphorus Content of Steel in a Scrap-Based Electric Arc Furnace Using Artificial Neural Networks
Riadh Azzaz
Valentin Hurel
Patrice Ménard
M. Jahazi
S Ebrahimi Kahou
Elmira Moosavi-Khoonsari
2024-10-24
ArXiv (preprint)
doi.org
arxiv.org
ConvNTC: Convolutional neural tensor completion for predicting the disease-related miRNA pairs and cell-related drug pairs
Pei Liu
Xiao Liang
Yuemei Li
Jiawei Luo
2024-10-23
bioRxiv (preprint)
doi.org
The roles of neural networks in language acquisition
Eva Portelance
Masoud Jasbi

How can modern neural networks like large language models be useful to the field of language acquisition, and more broadly cognitive scie… (see more)nce, if they are not a priori designed to be cognitive models? As developments towards natural language understanding and generation have improved leaps and bounds, with models like GPT-4, the question of how they can inform our understanding of human language acquisition has re-emerged. As such, it is critical to examine how in practice linking hypotheses between models and human learners can be safely established. To address these questions, we propose a model taxonomy, including four modeling approaches, each having differing goals, from exploratory hypothesis generation to hypothesis differentiation and testing. We show how the goals of these approaches align with the overarching goals of science and linguistics by connecting our taxonomy to the realist vs. instrumentalist approaches in philosophy of science. We survey recent work having adopted each of our modelling approaches and address the importance of computational modelling in language acquisition studies.

2024-10-23
Language and Linguistics Compass (published)
doi.org
Minimally Invasive Morphology Adaptation via Parameter Efficient Fine-Tuning
Michael Przystupa
Hongyao Tang
Mariano Phielipp
Santiago Miret
Martin Jagersand
Glen Berseth
Learning reinforcement learning policies to control individual robots is often computationally non-economical because minor variations in ro… (see more)bot morphology (e.g. dynamics or number of limbs) can negatively impact policy performance. This limitation has motivated morphology agnostic policy learning, in which a monolithic deep learning policy learns to generalize between robotic morphologies. Unfortunately, these policies still have sub-optimal zero-shot performance compared to end-to-end finetuning on target morphologies. This limitation has ramifications in practical robotic applications, as online finetuning large neural networks can require immense computation. In this work, we investigate \textit{parameter efficient finetuning} techniques to specialize morphology-agnostic policies to a target robot that minimizes the number of learnable parameters adapted during online learning. We compare direct finetuning, which update subsets of the base model parameters, and input-learnable approaches, which add additional parameters to manipulate inputs passed to the base model. Our analysis concludes that tuning relatively few parameters (0.01\% of the base model) can measurably improve policy performance over zero shot. These results serve a prescriptive purpose for future research for which scenarios certain PEFT approaches are best suited for adapting policy's to new robotic morphologies.
2024-10-22
corl.org/2024/Workshop/MAPoDeL (published)
openreview.net
openreview.net
Multilingual Hallucination Gaps in Large Language Models
Cl'ea Chataigner
Afaf Taïk
Golnoosh Farnadi
Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that … (see more)resembles human language. However, this shift is concerning, as LLMs often generate hallucinations, misleading or false information that appears highly credible. In this study, we explore the phenomenon of hallucinations across multiple languages in freeform text generation, focusing on what we call multilingual hallucination gaps. These gaps reflect differences in the frequency of hallucinated answers depending on the prompt and language used. To quantify such hallucinations, we used the FactScore metric and extended its framework to a multilingual setting. We conducted experiments using LLMs from the LLaMA, Qwen, and Aya families, generating biographies in 19 languages and comparing the results to Wikipedia pages. Our results reveal variations in hallucination rates, especially between high and low resource languages, raising important questions about LLM multilingual performance and the challenges in evaluating hallucinations in multilingual freeform text generation.
2024-10-22
ArXiv (preprint)
doi.org
arxiv.org
Overcoming State and Action Space Disparities in Multi-Domain, Multi-Task Reinforcement Learning
Reginald McLean
Kai Yuan
Isaac Woungang
Nariman Farsad
Pablo Samuel Castro
Current multi-task reinforcement learning (MTRL) methods have the ability to perform a large number of tasks with a single policy. However w… (see more)hen attempting to interact with a new domain, the MTRL agent would need to be re-trained due to differences in domain dynamics and structure. Because of these limitations, we are forced to train multiple policies even though tasks may have shared dynamics, leading to needing more samples and is thus sample inefficient. In this work, we explore the ability of MTRL agents to learn in various domains with various dynamics by simultaneously learning in multiple domains, without the need to fine-tune extra policies. In doing so we find that a MTRL agent trained in multiple domains induces an increase in sample efficiency of up to 70\% while maintaining the overall success rate of the MTRL agent.
2024-10-22
corl.org/2024/Workshop/MAPoDeL (published)
openreview.net
openreview.net
Scaling Stick-Breaking Attention: An Efficient Implementation and In-Depth Study
Shawn Tan
Yikang Shen
Songlin Yang
Aaron Courville
Rameswar Panda
The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases… (see more) to account for token order. But current methods using still face length generalisation challenges. We investigate an alternative attention mechanism based on the stick-breaking process in larger scale settings. The method works as follows: For each token before the current, we determine a break point, which represents the proportion of the stick, the weight of the attention, to allocate to the current token. We repeat this on the remaining stick, until all tokens are allocated a weight, resulting in a sequence of attention weights. This process naturally incorporates recency bias, which has linguistic motivations for grammar parsing. We study the implications of replacing the conventional softmax-based attention mechanism with stick-breaking attention. We then discuss implementation of numerically stable stick-breaking attention and adapt Flash Attention to accommodate this mechanism. When used as a drop-in replacement for current softmax+RoPE attention systems, we find that stick-breaking attention performs competitively with current methods on length generalisation and downstream tasks. Stick-breaking also performs well at length generalisation, allowing a model trained with
2024-10-22
ArXiv (preprint)
doi.org
openreview.net
Symmetry-Aware Generative Modeling through Learned Canonicalization
Kusha Sareen
Daniel Levy
Arnab Kumar Mondal
Sékou-Oumar Kaba
Tara Akhound-Sadegh
Siamak Ravanbakhsh
Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The ex… (see more)isting generative modeling paradigm for invariant densities combines an invariant prior with an equivariant generative process. However, we observe that this technique is not necessary and has several drawbacks resulting from the limitations of equivariant networks. Instead, we propose to model a learned slice of the density so that only one representative element per orbit is learned. To accomplish this, we learn a group-equivariant canonicalization network that maps training samples to a canonical pose and train a non-equivariant generative model over these canonicalized samples. We implement this idea in the context of diffusion models. Our preliminary experimental results on molecular modeling are promising, demonstrating improved sample quality and faster inference time.
2024-10-22
NeurIPS.cc/2024/Workshop/NeurReps (poster)
doi.org
openreview.net