AIConfPaper
← Search

Thomas Jiralerspong

5 accepted papers

2025

Expressivity of Neural Networks with Random Weights and Learned Biases

Ezekiel Williams, Alexandre Payeur, Avery Hee-Woon Ryoo, Thomas Jiralerspong, Matthew G Perich, Luca Mazzucato +1
ICLR 2025poster

Landmark universal function approximation results for neural networks with trained weights and biases provided the impetus for the ubiquitous use of neural networks as learning models in neuroscience and Artificial Intelligence (AI). Recent work has extended these results to networks in which a smal…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

Geometric Signatures of Compositionality Across a Language Model’s Lifetime

Jin Hwa Lee, Thomas Jiralerspong, Lei Yu, Yoshua Bengio, Emily Cheng
ACL 2025long

By virtue of linguistic compositionality, few syntactic rules and a finite lexicon can generate an unbounded number of sentences. That is, language, though seemingly high-dimensional, can be explained using relatively few degrees of freedom. An open question is whether contemporary language models (…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Towards a Formal Theory of Representational Compositionality

Eric Elmoznino, Thomas Jiralerspong, Yoshua Bengio, Guillaume Lajoie
ICML 2025poster

Compositionality is believed to be fundamental to intelligence. In humans, it underlies the structure of thought and language. In AI, it enables a powerful form of out-of-distribution generalization, in which a model systematically adapts to novel combinations of known concepts. However, while we ha…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL

Chen Sun, Wannan Yang, Thomas Jiralerspong, Dane Malenfant, Benjamin Alsbury-Nealy, Yoshua Bengio +1
NeurIPS 2023poster

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 are challenging to identify with traditional reinforcement learning (RL) methods that rely on the Bellman equation for credit assignment. He…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2023

Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning

Flemming Kondrup, Thomas Jiralerspong, Elaine Lau, Nathan de Lara, Jacob Shkrob, My Duc Tran +2
AAAI 2023technical

Mechanical ventilation is a key form of life support for patients with pulmonary impairment. Healthcare workers are required to continuously adjust ventilator settings for each patient, a challenging and time consuming task. Hence, it would be beneficial to develop an automated decision support tool…

Cited by 29Source ↗PDF ↗code ↗Scholar ↗