AI Medical Compendium Journal:
The Behavioral and brain sciences

Showing 11 to 20 of 76 articles

Comprehensive assessment methods are key to progress in deep learning.

The Behavioral and brain sciences
Bowers et al. eloquently describe issues with current deep neural network (DNN) models of vision, claiming that there are deficits both with the methods of assessment, and with the models themselves. I am in agreement with both these claims, but prop...

Fixing the problems of deep neural networks will require better training data and learning algorithms.

The Behavioral and brain sciences
Bowers et al. argue that deep neural networks (DNNs) are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as D...

For deep networks, the whole equals the sum of the parts.

The Behavioral and brain sciences
Deep convolutional networks exceed humans in sensitivity to local image properties, but unlike biological vision systems, do not discover and encode abstract relations that capture important properties of objects and events in the world. Coupling net...

Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses.

The Behavioral and brain sciences
An ideal vision model accounts for behavior and neurophysiology in both naturalistic conditions and designed lab experiments. Unlike psychological theories, artificial neural networks (ANNs) actually perform visual tasks and generate testable predict...

Why psychologists should embrace rather than abandon DNNs.

The Behavioral and brain sciences
Deep neural networks (DNNs) are powerful computational models, which generate complex, high-level representations that were missing in previous models of human cognition. By studying these high-level representations, psychologists can now gain new in...

For human-like models, train on human-like tasks.

The Behavioral and brain sciences
Bowers et al. express skepticism about deep neural networks (DNNs) as models of human vision due to DNNs' failures to account for results from psychological research. We argue that to fairly assess DNNs, we must first train them on more human-like ta...

Let's move forward: Image-computable models and a common model evaluation scheme are prerequisites for a scientific understanding of human vision.

The Behavioral and brain sciences
In the target article, Bowers et al. dispute deep artificial neural network (ANN) models as the currently leading models of human vision without producing alternatives. They eschew the use of public benchmarking platforms to compare vision models wit...

Psychophysics may be the game-changer for deep neural networks (DNNs) to imitate the human vision.

The Behavioral and brain sciences
Psychologically faithful deep neural networks (DNNs) could be constructed by training with psychophysics data. Moreover, conventional DNNs are mostly monocular vision based, whereas the human brain relies mainly on binocular vision. DNNs developed as...

Clarifying status of DNNs as models of human vision.

The Behavioral and brain sciences
On several key issues we agree with the commentators. Perhaps most importantly, everyone seems to agree that psychology has an important role to play in building better models of human vision, and (most) everyone agrees (including us) that deep neura...

and in deep neural network models of neurological network functions.

The Behavioral and brain sciences
Depending on what we mean by "explanation," challenges to the explanatory depth and reach of deep neural network models of visual and other forms of intelligent behavior may need revisions to both the elementary building blocks of neural nets (the ex...