Zobrazeno 1 - 10
of 857
pro vyhledávání: '"Murphy, Kieran A."'
Disentanglement is the endeavour to use machine learning to divide information about a dataset into meaningful fragments. In practice these fragments are representation (sub)spaces, often the set of channels in the latent space of a variational autoe
Externí odkaz:
http://arxiv.org/abs/2405.21042
Autor:
Ouellet, Mathieu, Bassett, Dani S., Bassett, Lee C., Murphy, Kieran A., Patankar, Shubhankar P.
Prions are misfolded proteins that transmit their structural arrangement to neighboring proteins. In biological systems, prion dynamics can produce a variety of complex functional outcomes. Yet, an understanding of prionic causes has been hampered by
Externí odkaz:
http://arxiv.org/abs/2402.10939
Autor:
Murphy, Kieran A., Bassett, Dani S.
Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is challenging, a
Externí odkaz:
http://arxiv.org/abs/2311.04896
Autor:
Patankar, Shubhankar P., Ouellet, Mathieu, Cervino, Juan, Ribeiro, Alejandro, Murphy, Kieran A., Bassett, Dani S.
Intrinsically motivated exploration has proven useful for reinforcement learning, even without additional extrinsic rewards. When the environment is naturally represented as a graph, how to guide exploration best remains an open question. In this wor
Externí odkaz:
http://arxiv.org/abs/2307.04962
Autor:
Murphy, Kieran A., Bassett, Dani S.
Publikováno v:
PNAS 121 (2024) e2312988121
One of the fundamental steps toward understanding a complex system is identifying variation at the scale of the system's components that is most relevant to behavior on a macroscopic scale. Mutual information provides a natural means of linking varia
Externí odkaz:
http://arxiv.org/abs/2307.04755
Autor:
Murphy, Kieran A., Bassett, Dani S.
Publikováno v:
ICLR 2023
Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible but at the
Externí odkaz:
http://arxiv.org/abs/2211.17264
Autor:
Murphy, Kieran A., Bassett, Dani S.
A hallmark of chaotic dynamics is the loss of information with time. Although information loss is often expressed through a connection to Lyapunov exponents -- valid in the limit of high information about the system state -- this picture misses the r
Externí odkaz:
http://arxiv.org/abs/2210.14220
Autor:
Murphy, Kieran A., Bassett, Dani S.
The fruits of science are relationships made comprehensible, often by way of approximation. While deep learning is an extremely powerful way to find relationships in data, its use in science has been hindered by the difficulty of understanding the le
Externí odkaz:
http://arxiv.org/abs/2204.07576
Single image pose estimation is a fundamental problem in many vision and robotics tasks, and existing deep learning approaches suffer by not completely modeling and handling: i) uncertainty about the predictions, and ii) symmetric objects with multip
Externí odkaz:
http://arxiv.org/abs/2106.05965
Representational learning forms the backbone of most deep learning applications, and the value of a learned representation is intimately tied to its information content regarding different factors of variation. Finding good representations depends on
Externí odkaz:
http://arxiv.org/abs/2103.03240