Lessons from infant learning for unsupervised machine learning
The desire to reduce the dependence on curated, labeled datasets and to leverage the vast
quantities of unlabeled data has triggered renewed interest in unsupervised (or self …
quantities of unlabeled data has triggered renewed interest in unsupervised (or self …
Learning long-range spatial dependencies with horizontal gated recurrent units
Progress in deep learning has spawned great successes in many engineering applications.
As a prime example, convolutional neural networks, a type of feedforward neural networks …
As a prime example, convolutional neural networks, a type of feedforward neural networks …
Recurrent neural circuits for contour detection
We introduce a deep recurrent neural network architecture that approximates visual cortical
circuits. We show that this architecture, which we refer to as the gamma-net, learns to solve …
circuits. We show that this architecture, which we refer to as the gamma-net, learns to solve …
Disentangling neural mechanisms for perceptual grouping
Forming perceptual groups and individuating objects in visual scenes is an essential step
towards visual intelligence. This ability is thought to arise in the brain from computations …
towards visual intelligence. This ability is thought to arise in the brain from computations …
Illusions, delusions, and your backwards bayesian brain: a biased visual perspective
RT Born, GM Bencomo - Brain Behavior and Evolution, 2021 - karger.com
The retinal image is insufficient for determining what is “out there,” because many different
real-world geometries could produce any given retinal image. Thus, the visual system must …
real-world geometries could produce any given retinal image. Thus, the visual system must …
[图书][B] Optimally irrational: The good reasons we behave the way we do
L Page - 2022 - books.google.com
For a long time, economists have assumed that we were cold, self-centred, rational decision
makers–so-called Homo economicus; the last few decades have shattered this view. The …
makers–so-called Homo economicus; the last few decades have shattered this view. The …
Innovative Analysis Ready Data (ARD) product and process requirements, software system design, algorithms and implementation at the midstream as necessary-but …
A Baraldi, LD Sapia, D Tiede, M Sudmanns… - Big Earth …, 2023 - Taylor & Francis
Aiming at the convergence between Earth observation (EO) Big Data and Artificial General
Intelligence (AGI), this two-part paper identifies an innovative, but realistic EO optical …
Intelligence (AGI), this two-part paper identifies an innovative, but realistic EO optical …
A comparative biology approach to DNN modeling of vision: A focus on differences, not similarities
Deep neural networks (DNNs) have revolutionized computer science and are now widely
used for neuroscientific research. A hot debate has ensued about the usefulness of DNNs as …
used for neuroscientific research. A hot debate has ensued about the usefulness of DNNs as …
Visual attention emerges from recurrent sparse reconstruction
Visual attention helps achieve robust perception under noise, corruption, and distribution
shifts in human vision, which are areas where modern neural networks still fall short. We …
shifts in human vision, which are areas where modern neural networks still fall short. We …
Tracking without re-recognition in humans and machines
Imagine trying to track one particular fruitfly in a swarm of hundreds. Higher biological visual
systems have evolved to track moving objects by relying on both their appearance and their …
systems have evolved to track moving objects by relying on both their appearance and their …