Physiological signal variability in hMT+ reflects performance on a direction discrimination task

Autor: Magdalena Graciela Wutte, Michael Thomas Smith, Virginia L. eFlanagin, Thomas eWolbers

Publikováno v: Frontiers in Psychology, Vol 2 (2011)

Our ability to perceive visual motion is critically dependent on the human motion complex (hMT+) in the dorsal visual stream. Extensive electrophysiological research in the monkey equivalent of this region has demonstrated how neuronal populations co

Externí odkaz: https://doaj.org/article/70e80ea8b0f743bab402e675f6382b8b

Adversarial vulnerability bounds for Gaussian process classification

Autor: Michael Thomas Smith, Kathrin Grosse, Michael Backes, Mauricio A. Álvarez

Publikováno v: Machine Learning. 112:971-1009

Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d617416881fa6cab639220270ef151bb
https://doi.org/10.1007/s10994-022-06224-6

Abraham Lincoln, Manhood, and Nineteenth-Century American Political Culture

Autor: Michael Thomas Smith

Publikováno v: This Distracted and Anarchical People: New Answers for Old Questions about the Civil War-Era North

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e67073ba8521facd61bc1411148ef658
https://doi.org/10.1515/9780823293384-005

Author response for 'A method for low‐cost, low‐impact insect tracking using retroreflective tags'

Autor: null Michael Thomas Smith, null Michael Livingstone, null Richard Comont

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a62b0c46b5d5a6fd590d20ecb5bcd854
https://doi.org/10.1111/2041-210x.13699/v2/response1

Differentially Private Regression and Classification with Sparse Gaussian Processes

Autor: Michael Thomas Smith, Mauricio A. Álvarez, Lawrence, Neil D.

Publikováno v: University of Manchester-PURE
Smith, M T, Álvarez, M A & Lawrence, N D 2021, ' Differentially Private Regression and Classification with Sparse Gaussian Processes ', Journal of Machine Learning Research, vol. 22 . < https://proceedings.mlr.press/v84/smith18a.html >

A continuing challenge for machine learning is providing methods to perform computation on data while ensuring the data remains private. In this paper we build on the provable privacy guarantees of differential privacy which has been combined with Ga

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c840109c30faa0014ced6ca8c9dd15a5
http://arxiv.org/abs/1909.09147