Search Results - "Jiralerspong, Thomas"

  • Showing 1 - 12 results of 12
Refine Results
  1. 1

    Network Analysis of the iNaturalist Citizen Science Community by Liu, Yu Lu, Jiralerspong, Thomas

    Published 15-10-2023
    “…In recent years, citizen science has become a larger and larger part of the scientific community. Its ability to crowd source data and expertise from thousands…”
    Get full text
    Journal Article
  2. 2

    General Causal Imputation via Synthetic Interventions by Jiralerspong, Marco, Jiralerspong, Thomas, Shah, Vedant, Sridhar, Dhanya, Gidel, Gauthier

    Published 27-10-2024
    “…Given two sets of elements (such as cell types and drug compounds), researchers typically only have access to a limited subset of their interactions. The task…”
    Get full text
    Journal Article
  3. 3

    A Complexity-Based Theory of Compositionality by Elmoznino, Eric, Jiralerspong, Thomas, Bengio, Yoshua, Lajoie, Guillaume

    Published 18-10-2024
    “…Compositionality is believed to be fundamental to intelligence. In humans, it underlies the structure of thought, language, and higher-level reasoning. In AI,…”
    Get full text
    Journal Article
  4. 4

    Efficient Causal Graph Discovery Using Large Language Models by Jiralerspong, Thomas, Chen, Xiaoyin, More, Yash, Shah, Vedant, Bengio, Yoshua

    Published 02-02-2024
    “…We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this…”
    Get full text
    Journal Article
  5. 5

    A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control by Wang, Marshall, Willes, John, Jiralerspong, Thomas, Moezzi, Matin

    Published in 2023 IEEE Smart World Congress (SWC) (28-08-2023)
    “…Reinforcement learning (RL) is a promising approach for optimizing HVAC control. RL offers a framework for improving system performance, reducing energy…”
    Get full text
    Conference Proceeding
  6. 6

    Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels by Jiralerspong, Thomas, Kondrup, Flemming, Precup, Doina, Khetarpal, Khimya

    Published 15-10-2023
    “…The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and thus enables…”
    Get full text
    Journal Article
  7. 7

    A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control by Wang, Marshall, Willes, John, Jiralerspong, Thomas, Moezzi, Matin

    Published 10-08-2023
    “…Reinforcement learning (RL) is a promising approach for optimizing HVAC control. RL offers a framework for improving system performance, reducing energy…”
    Get full text
    Journal Article
  8. 8

    Geometric Signatures of Compositionality Across a Language Model's Lifetime by Lee, Jin Hwa, Jiralerspong, Thomas, Yu, Lei, Bengio, Yoshua, Cheng, Emily

    Published 02-10-2024
    “…Compositionality, the notion that the meaning of an expression is constructed from the meaning of its parts and syntactic rules, permits the infinite…”
    Get full text
    Journal Article
  9. 9

    Expressivity of Neural Networks with Random Weights and Learned Biases by Williams, Ezekiel, Ryoo, Avery Hee-Woon, Jiralerspong, Thomas, Payeur, Alexandre, Perich, Matthew G, Mazzucato, Luca, Lajoie, Guillaume

    Published 01-07-2024
    “…Landmark universal function approximation results for neural networks with trained weights and biases provided impetus for the ubiquitous use of neural…”
    Get full text
    Journal Article
  10. 10

    Delta-AI: Local objectives for amortized inference in sparse graphical models by Falet, Jean-Pierre, Lee, Hae Beom, Malkin, Nikolay, Sun, Chen, Secrieru, Dragos, Jiralerspong, Thomas, Zhang, Dinghuai, Lajoie, Guillaume, Bengio, Yoshua

    Published 03-10-2023
    “…We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\Delta$-amortized inference ($\Delta$-AI)…”
    Get full text
    Journal Article
  11. 11

    Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL by Sun, Chen, Yang, Wannan, Jiralerspong, Thomas, Malenfant, Dane, Alsbury-Nealy, Benjamin, Bengio, Yoshua, Richards, Blake

    Published 11-10-2022
    “…In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. These critical steps…”
    Get full text
    Journal Article
  12. 12

    Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning by Kondrup, Flemming, Jiralerspong, Thomas, Lau, Elaine, de Lara, Nathan, Shkrob, Jacob, Tran, My Duc, Precup, Doina, Basu, Sumana

    Published 05-10-2022
    “…Mechanical ventilation is a key form of life support for patients with pulmonary impairment. Healthcare workers are required to continuously adjust ventilator…”
    Get full text
    Journal Article