An approach to cognitive science that models mental/behavioral phenomena as an emergent process of interconnected networks of simple units.

learn more… | top users | synonyms

3
votes
2answers
90 views

Neurosurgically grown neural link between two brains?

I guess it's possible to surgically restore neural connection after a trauma (e.g. a severed hand can be reattached if done quickly). And, from history of evolution of hominids, it seems that just by ...
9
votes
1answer
146 views

How does evolution help in Minsky's theory of a resourceful mind?

I've read Minsky's book The Emotion Machine, where he explains how the mind can be seen as a set of resources interacting and self-interacting based on several levels of change. The explanation is in ...
5
votes
2answers
124 views

Any models that act using both streams of visual processing?

The Two-Stream Hypothesis, where object properties are processed independently from spatial information, remains the most well established theory of visual processing. However, it concerns me that ...
8
votes
0answers
285 views

Modern treatments of Alan Turing's B-type neural networks

In the cognitive sciences Alan Turing is best known for launching AI with his Computing machinery and intelligence (1950). However, this was not his first contribution to the cognitive sciences, in ...
4
votes
3answers
119 views

Are there any cognitive models for visual navigation?

I've seen a few neuroscience accounts of visual navigation and many A.I. projects, but no psychologically plausible accounts that actually solve the computational problem (i.e. produce a working ...
7
votes
1answer
121 views

How can STDP fit with reciprocal connectivity?

I have rather technical question regarding STDP dynamics. I am working on a neural network implementing an STDP learning algorithm, and have noticed that it is extremely anti-reciprocal. When two ...
9
votes
1answer
213 views

Are there any connectionist models that integrate reinforcement and fully supervised learning?

I've been working on modeling some phenomena involving real-time control in an environment with inherent rewards (specifically, playing a 'pong'-like game), and it's increasingly looking like ...
6
votes
2answers
120 views

Utility or software to visualize Neural Network?

I am using Octave to generate a Neural Network with a single hidden layer, and saving it as two CSV files. Is there a utility or software that will load the files and create an image, PDF or HTML ...
9
votes
1answer
499 views

Spurious attractors in Hopfield networks

A classic "Hopfield network" is a type of artificial neural network in which the units are bi-stable and fully interconnected by symmetrically weighted connections. In 1982, Hopfield showed that such ...