Search Results for author: Francisco Pereira

Found 16 papers, 5 papers with code

Testing for context-dependent changes in neural encoding in naturalistic experiments

no code implementations17 Nov 2022 Yenho Chen, Carl W. Harris, Xiaoyu Ma, Zheng Li, Francisco Pereira, Charles Y. Zheng

We propose a decoding-based approach to detect context effects on neural codes in longitudinal neural recording data.

Representation learning of rare temporal conditions for travel time prediction

no code implementations9 Aug 2022 Niklas Petersen, Filipe Rodrigues, Francisco Pereira

We present a vector-space model for encoding rare temporal conditions, that allows coherent representation learning across different temporal conditions.

Representation Learning Time Series Analysis

VICE: Variational Interpretable Concept Embeddings

1 code implementation2 May 2022 Lukas Muttenthaler, Charles Y. Zheng, Patrick McClure, Robert A. Vandermeulen, Martin N. Hebart, Francisco Pereira

This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task.

Experimental Design Odd One Out +2

Understanding Mental Representations Of Objects Through Verbs Applied To Them

no code implementations1 Jan 2021 Ka Chun Lam, Francisco Pereira, Maryam Vaziri-Pashkam, Kristin Woodard, Emalie McMahon

Finally, we show that the dimensions can be used to predict a state-of-the-art mental representation of objects, derived purely from human judgements of object similarity.

A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes

1 code implementation8 Sep 2020 Patrick McClure, Gabrielle Reimann, Michal Ramot, Francisco Pereira

This short article describes a deep neural network trained to perform automatic segmentation of human body parts in natural scenes.

Mental representations of objects reflect the ways in which we interact with them

no code implementations22 Jun 2020 Ka Chun Lam, Francisco Pereira, Maryam Vaziri-Pashkam, Kristin Woodard, Emalie McMahon

In order to interact with objects in our environment, humans rely on an understanding of the actions that can be performed on them, as well as their properties.

Improving the Interpretability of fMRI Decoding using Deep Neural Networks and Adversarial Robustness

1 code implementation23 Apr 2020 Patrick McClure, Dustin Moraczewski, Ka Chun Lam, Adam Thomas, Francisco Pereira

We introduce two quantitative evaluation procedures for saliency map methods in fMRI, applicable whenever a DNN or linear model is being trained to decode some information from imaging data.

Adversarial Robustness

Bayesian Automatic Relevance Determination for Utility Function Specification in Discrete Choice Models

no code implementations10 Jun 2019 Filipe Rodrigues, Nicola Ortelli, Michel Bierlaire, Francisco Pereira

Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices.

Bayesian Inference Variational Inference

Revealing interpretable object representations from human behavior

no code implementations ICLR 2019 Charles Y. Zheng, Francisco Pereira, Chris I. Baker, Martin N. Hebart

To study how mental object representations are related to behavior, we estimated sparse, non-negative representations of objects using human behavioral judgments on images representative of 1, 854 object categories.

Knowing what you know in brain segmentation using Bayesian deep neural networks

1 code implementation3 Dec 2018 Patrick McClure, Nao Rho, John A. Lee, Jakub R. Kaczmarzyk, Charles Zheng, Satrajit S. Ghosh, Dylan Nielson, Adam G. Thomas, Peter Bandettini, Francisco Pereira

In this paper, we describe a Bayesian deep neural network (DNN) for predicting FreeSurfer segmentations of structural MRI volumes, in minutes rather than hours.

Brain Segmentation Variational Inference

Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach

no code implementations16 Aug 2018 Filipe Rodrigues, Ioulia Markou, Francisco Pereira

Accurate time-series forecasting is vital for numerous areas of application such as transportation, energy, finance, economics, etc.

Time Series Forecasting Word Embeddings

Distributed Weight Consolidation: A Brain Segmentation Case Study

no code implementations NeurIPS 2018 Patrick McClure, Charles Y. Zheng, Jakub R. Kaczmarzyk, John A. Lee, Satrajit S. Ghosh, Dylan Nielson, Peter Bandettini, Francisco Pereira

Collecting the large datasets needed to train deep neural networks can be very difficult, particularly for the many applications for which sharing and pooling data is complicated by practical, ethical, or legal concerns.

Brain Segmentation Continual Learning

Semantic projection: recovering human knowledge of multiple, distinct object features from word embeddings

no code implementations5 Feb 2018 Gabriel Grand, Idan Asher Blank, Francisco Pereira, Evelina Fedorenko

Because related words appear in similar contexts, such spaces - called "word embeddings" - can be learned from patterns of lexical co-occurrences in natural language.

Word Embeddings

Deep learning from crowds

3 code implementations6 Sep 2017 Filipe Rodrigues, Francisco Pereira

Over the last few years, deep learning has revolutionized the field of machine learning by dramatically improving the state-of-the-art in various domains.

A systematic approach to extracting semantic information from functional MRI data

no code implementations NeurIPS 2012 Francisco Pereira, Matthew Botvinick

This paper introduces a novel classification method for functional magnetic resonance imaging datasets with tens of classes.

General Classification

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