AI Medical Compendium Journal:
The Behavioral and brain sciences

Showing 21 to 30 of 76 articles

A deep new look at color.

The Behavioral and brain sciences
Bowers et al. counter deep neural networks (DNNs) as good models of human visual perception. From our color perspective we feel their view is based on three misconceptions: A misrepresentation of the state-of-the-art of color perception; the type of ...

There is a fundamental, unbridgeable gap between DNNs and the visual cortex.

The Behavioral and brain sciences
Deep neural networks (DNNs) are not just inadequate models of the visual system but are so different in their structure and functionality that they are not even on the same playing field. DNN units have almost nothing in common with neurons, and, unl...

Perceptual learning in humans: An active, top-down-guided process.

The Behavioral and brain sciences
Deep neural network (DNN) models of human-like vision are typically built by feeding blank slate DNN visual images as training data. However, the literature on human perception and perceptual learning suggests that developing DNNs that truly model hu...

Neural networks need real-world behavior.

The Behavioral and brain sciences
Bowers et al. propose to use controlled behavioral experiments when evaluating deep neural networks as models of biological vision. We agree with the sentiment and draw parallels to the notion that "neuroscience needs behavior." As a promising path f...

The scientific value of explanation and prediction.

The Behavioral and brain sciences
Deep neural network models have revived long-standing debates on the value of explanation versus prediction for advancing science. Bowers et al.'s critique will not make these models go away, but it is likely to prompt new work that seeks to reconcil...

Modelling human vision needs to account for subjective experience.

The Behavioral and brain sciences
Vision is inseparably connected to perceptual awareness which can be seen as the culmination of sensory processing. Studies on conscious vision reveal that object recognition is just one of the means through which our representation of the world is b...

Neither hype nor gloom do DNNs justice.

The Behavioral and brain sciences
Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNNs rapidly evolve, and today's limitations are often tomorrow's success...

Moral artificial intelligence and machine puritanism.

The Behavioral and brain sciences
Puritanism may evolve into a technological variant based on norms of delegation of actions and perceptions to artificial intelligence. Instead of training self-control, people may be expected to cede their agency to self-controlled machines. The cost...

Fractals and artificial intelligence to decrypt ideography and understand the evolution of language.

The Behavioral and brain sciences
Self-sufficient ideographies are rare because they are stifled by the issue of standardization. Similar issues arise with abstract art or drawings created by young children or great apes. We propose that mathematical indices and artificial intelligen...

Neither neural networks nor the language-of-thought alone make a complete game.

The Behavioral and brain sciences
Cognitive science has evolved since early disputes between radical empiricism and radical nativism. The authors are reacting to the revival of radical empiricism spurred by recent successes in deep neural network (NN) models. We agree that language-l...