Search Results for author: Talia Konkle

Found 7 papers, 2 papers with code

Feature Accentuation: Revealing 'What' Features Respond to in Natural Images

no code implementations15 Feb 2024 Chris Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George Alvarez

Most research has primarily centered around attribution methods, which provide explanations in the form of heatmaps, showing where the model directs its attention for a given feature.

How does the primate brain combine generative and discriminative computations in vision?

no code implementations11 Jan 2024 Benjamin Peters, James J. DiCarlo, Todd Gureckis, Ralf Haefner, Leyla Isik, Joshua Tenenbaum, Talia Konkle, Thomas Naselaris, Kimberly Stachenfeld, Zenna Tavares, Doris Tsao, Ilker Yildirim, Nikolaus Kriegeskorte

The alternative conception is that of vision as an inference process in Helmholtz's sense, where the sensory evidence is evaluated in the context of a generative model of the causal processes giving rise to it.

The neuroconnectionist research programme

no code implementations8 Sep 2022 Adrien Doerig, Rowan Sommers, Katja Seeliger, Blake Richards, Jenann Ismael, Grace Lindsay, Konrad Kording, Talia Konkle, Marcel A. J. van Gerven, Nikolaus Kriegeskorte, Tim C. Kietzmann

Artificial Neural Networks (ANNs) inspired by biology are beginning to be widely used to model behavioral and neural data, an approach we call neuroconnectionism.


Pruning for Feature-Preserving Circuits in CNNs

1 code implementation3 Jun 2022 Chris Hamblin, Talia Konkle, George Alvarez

Deep convolutional neural networks are a powerful model class for a range of computer vision problems, but it is difficult to interpret the image filtering process they implement, given their sheer size.

Network Pruning

What can 5.17 billion regression fits tell us about artificial models of the human visual system?

no code implementations NeurIPS Workshop SVRHM 2021 Colin Conwell, Jacob S. Prince, George A. Alvarez, Talia Konkle

Rapid simultaneous advances in machine vision and cognitive neuroimaging present an unparalleled opportunity to assess the current state of artificial models of the human visual system.


Emergent Properties of Foveated Perceptual Systems

2 code implementations14 Jun 2020 Arturo Deza, Talia Konkle

The primary model has a foveated-textural input stage, which we compare to a model with foveated-blurred input and a model with spatially-uniform blurred input (both matched for perceptual compression), and a final reference model with minimal input-based compression.

Foveation Scene Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.