Publications

Player-Guided AI outperforms standard AI in Sequence Alignment Puzzles
Renata Mutalova
Roman Sarrazin-Gendron
Parham Ghasemloo Gheidari
Eddie Cai
Gabriel Richard
Sébastien Caisse
Rob Knight
Mathieu Blanchette
Attila Szantner
Jérôme Waldispühl
2023-11-05
International Conference on Climate Informatics (published)
doi.org
The feature landscape of visual cortex
Rudi Tong
Ronan da Silva
Dongyan Lin
Arna Ghosh
James Wilsenach
Erica Cianfarano
Pouya Bashivan
Blake Richards
Stuart Trenholm
Understanding computations in the visual system requires a characterization of the distinct feature preferences of neurons in different visu… (see more)al cortical areas. However, we know little about how feature preferences of neurons within a given area relate to that area’s role within the global organization of visual cortex. To address this, we recorded from thousands of neurons across six visual cortical areas in mouse and leveraged generative AI methods combined with closed-loop neuronal recordings to identify each neuron’s visual feature preference. First, we discovered that the mouse’s visual system is globally organized to encode features in a manner invariant to the types of image transformations induced by self-motion. Second, we found differences in the visual feature preferences of each area and that these differences generalized across animals. Finally, we observed that a given area’s collection of preferred stimuli (‘own-stimuli’) drive neurons from the same area more effectively through their dynamic range compared to preferred stimuli from other areas (‘other-stimuli’). As a result, feature preferences of neurons within an area are organized to maximally encode differences among own-stimuli while remaining insensitive to differences among other-stimuli. These results reveal how visual areas work together to efficiently encode information about the external world.
2023-11-05
bioRxiv (preprint)
doi.org
Score-Based Likelihood Characterization for Inverse Problems in the Presence of Non-Gaussian Noise
Ronan Legin
Alexandre Adam
Yashar Hezaveh
Laurence Perreault-Levasseur
Likelihood analysis is typically limited to normally distributed noise due to the difficulty of determining the probability density function… (see more) of complex, high-dimensional, non-Gaussian, and anisotropic noise. This work presents Score-based LIkelihood Characterization (SLIC), a framework that resolves this issue by building a data-driven noise model using a set of noise realizations from observations. We show that the approach produces unbiased and precise likelihoods even in the presence of highly non-Gaussian correlated and spatially varying noise. We use diffusion generative models to estimate the gradient of the probability density of noise with respect to data elements. In combination with the Jacobian of the physical model of the signal, we use Langevin sampling to produce independent samples from the unbiased likelihood. We demonstrate the effectiveness of the method using real data from the Hubble Space Telescope and James Webb Space Telescope.
2023-11-03
NeurIPS.cc/2023/Workshop/Deep_Inverse (poster)
openreview.net
openreview.net
Empowering Clinicians with MeDT: A Framework for Sepsis Treatment
Aamer Abdul Rahman
Pranav Agarwal
Vincent Michalski
Rita Noumeir
Samira Ebrahimi Kahou
2023-11-02
NeurIPS.cc/2023/Workshop/GCRL (published)
openreview.net
openreview.net
Goal Misgeneralization as Implicit Goal Conditioning
Diego Dorn
Neel Alex
David Scott Krueger
2023-11-02
NeurIPS.cc/2023/Workshop/GCRL (published)
openreview.net
openreview.net
How does fine-tuning affect your model? Mechanistic analysis on procedural tasks
Samyak Jain
Robert Kirk
Ekdeep Singh Lubana
Robert P. Dick
Hidenori Tanaka
Tim Rocktäschel
Edward Grefenstette
David Scott Krueger
Fine-tuning large pre-trained models has become the *de facto* strategy for developing models that are safe to deploy. However, there has be… (see more)en little work that explains how fine-tuning alters the underlying capabilities learnt by a model during pretraining: does fine-tuning yield entirely novel capabilities or does it just modulate existing ones? We address this question empirically in *synthetic* settings with mechanistic interpretability tools (e.g., network pruning and probing) to understand how the model's underlying capabilities are changing. Our extensive analysis of the effects of fine-tuning shows: (i) fine-tuning rarely alters the underlying model capabilities; (ii) a minimal transformation, which we call a 'wrapper', is typically learned on top of the underlying model capabilities; and (iii) further fine-tuning on a task where such wrapped capabilities are relevant leads to sample-efficient "revival'' of the capability, i.e., the model begins reusing this capability in a few gradient steps. *This indicates practitioners can unintentionally remove a model's safety wrapper by merely fine-tuning it on a superficially unrelated task.* We additionally perform analysis on language models trained on the TinyStories dataset to support our claims in a more realistic setup.
2023-11-02
NeurIPS.cc/2023/Workshop/UniReps (poster)
openreview.net
openreview.net
Multimodal and Force-Matched Imitation Learning with a See-Through Visuotactile Sensor
Trevor Ablett
Oliver Limoyo
Adam Sigal
Affan Jilani
Jonathan Kelly
Kaleem Siddiqi
Francois Hogan
Gregory Dudek
Kinesthetic Teaching is a popular approach to collecting expert robotic demonstrations of contact-rich tasks for imitation learning (IL), bu… (see more)t it typically only measures motion, ignoring the force placed on the environment by the robot. Furthermore, contact-rich tasks require accurate sensing of both reaching and touching, which can be difficult to provide with conventional sensing modalities. We address these challenges with a See-Through-your-Skin (STS) visuotactile sensor, using the sensor both (i) as a measurement tool to improve kinesthetic teaching, and (ii) as a policy input in contact-rich door manipulation tasks. An STS sensor can be switched between visual and tactile modes by leveraging a semi-transparent surface and controllable lighting, allowing for both pre-contact visual sensing and during-contact tactile sensing with a single sensor. First, we propose tactile force matching, a methodology that enables a robot to match forces read during kinesthetic teaching using tactile signals. Second, we develop a policy that controls STS mode switching, allowing a policy to learn the appropriate moment to switch an STS from its visual to its tactile mode. Finally, we study multiple observation configurations to compare and contrast the value of visual and tactile data from an STS with visual data from a wrist-mounted eye-in-hand camera. With over 3,000 test episodes from real-world manipulation experiments, we find that the inclusion of force matching raises average policy success rates by 62.5%, STS mode switching by 30.3%, and STS data as a policy input by 42.5%. Our results highlight the utility of see-through tactile sensing for IL, both for data collection to allow force matching, and for policy execution to allow accurate task feedback.
2023-11-02
ArXiv (preprint)
arxiv.org
arxiv.org
Pepid: a Highly Modifiable, Bioinformatics-Oriented Peptide Search Engine
Jeremie Zumer
Sébastien Lemieux
2023-11-02
bioRxiv (preprint)
doi.org
SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
Mélisande Teng
Amna Elmustafa
Benjamin Akera
Yoshua Bengio
Hager Radi
Hugo Larochelle
David Rolnick
Biodiversity is declining at an unprecedented rate, impacting ecosystem services necessary to ensure food, water, and human health and well-… (see more)being. Understanding the distribution of species and their habitats is crucial for conservation policy planning. However, traditional methods in ecology for species distribution models (SDMs) generally focus either on narrow sets of species or narrow geographical areas and there remain significant knowledge gaps about the distribution of species. A major reason for this is the limited availability of data traditionally used, due to the prohibitive amount of effort and expertise required for traditional field monitoring. The wide availability of remote sensing data and the growing adoption of citizen science tools to collect species observations data at low cost offer an opportunity for improving biodiversity monitoring and enabling the modelling of complex ecosystems. We introduce a novel task for mapping bird species to their habitats by predicting species encounter rates from satellite images, and present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird, considering summer (breeding) and winter seasons. We also provide a dataset in Kenya representing low-data regimes. We additionally provide environmental data and species range maps for each location. We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks. SatBird opens up possibilities for scalably modelling properties of ecosystems worldwide.
2023-11-02
ArXiv (preprint)
doi.org
arxiv.org
What Mechanisms Does Knowledge Distillation Distill?
Cindy Wu
Ekdeep Singh Lubana
Bruno Mlodozeniec
Robert Kirk
David Scott Krueger
2023-11-02
NeurIPS.cc/2023/Workshop/UniReps (poster)
openreview.net
openreview.net
Behavioral Imitation with Artificial Neural Networks Leads to Personalized Models of Brain Dynamics During Videogame Play
Anirudha Kemtur
Fraçois Paugam
Basile Pinsard
Yann Harel
Pravish Sainath
Maximilien Le Clei
Julie Boyle
Karim Jerbi
Lune Bellec
Artificial Neural networks (ANN) trained on complex tasks are increasingly used in neuroscience to model brain dynamics, a process called br… (see more)ain encoding. Videogames have been extensively studied in the field of artificial intelligence, but have hardly been used yet for brain encoding. Videogames provide a promising framework to understand brain activity in a rich, engaging, and active environment. A major challenge raised by complex videogames is that individual behavior is highly variable across subjects, and we hypothesized that ANNs need to account for subject-specific behavior in order to properly capture brain dynamics. In this study, we used ANNs to model functional magnetic resonance imaging (fMRI) and behavioral gameplay data, both collected while subjects played the Shinobi III videogame. Using imitation learning, we trained an ANN to play the game while closely replicating the unique gameplay style of individual participants. We found that hidden layers of our imitation learning model successfully encoded task-relevant neural representations, and predicted individual brain dynamics with higher accuracy than models trained on other subjects’ gameplay or control models. The highest correlations between layer activations and brain signals were observed in biologically plausible brain areas, i.e. somatosensory, attention, and visual networks. Our results demonstrate that combining imitation learning, brain imaging, and videogames can allow us to model complex individual brain patterns derived from decision making in a rich, complex environment.
2023-11-01
bioRxiv (preprint)
doi.org
Electric Power Fuse Identification With Deep Learning
Simon Giard-Leroux
Guillaume Cléroux
Shreyas Sunil Kulkarni
François Bouffard
Martin Vallières
As part of arc flash studies, survey pictures of electrical installations need to be manually analyzed. A challenging task is to identify fu… (see more)se types, which can be determined from physical characteristics, such as shape, color, and size. To automate this process using deep learning techniques, a new dataset of fuse pictures from past arc flash projects and data from the web was created. Multiple experiments were performed to train a final model, reaching an average precision of 91.06% on the holdout set, which confirms its potential for identification of fuse types in new photos. By identifying fuse types using physical characteristics only, the need to take clear pictures of the label text is eliminated, allowing pictures to be taken away from danger, thereby improving the safety of workers. All the resources needed to repeat the experiments are openly accessible, including the code and datasets.
2023-11-01
IEEE Transactions on Industrial Informatics (published)
doi.org