Show Reference: "Goal-directed learning of features and forward models"

Goal-directed learning of features and forward models Neural Networks, Vol. 22, No. 5. (2009) by S. Saeb, C. Weber, J. Triesch
    author = {Saeb, S. and Weber, C. and Triesch, J.},
    journal = {Neural Networks},
    keywords = {embodiment, learning, motor, prediction},
    number = {5},
    posted-at = {2013-06-10 09:21:37},
    priority = {2},
    publisher = {Elsevier},
    title = {Goal-directed learning of features and forward models},
    volume = {22},
    year = {2009},
    pages = {586--592}.
    volume = {22},
    number = {5--6},
    editor = {Robert Kozma, Steven Bressler, Leonid Perlovsky and Ganesh Kumar Venayagamoorthy}

See the CiteULike entry for more info, PDF links, BibTex etc.

Mixing Hebbian (unsupervised) learning with feedback can guide the unsupervised learning process in learning interesting, or task-relevant things.

Classical models assume that learning in cortical regions is well described in an unsupervised learning framework while learning in the basal ganglia can be modeled by reinforcement learning.

Representations in the cortex (eg. V1) develop differently depending on the task. This suggests that some sort of feedback signal might be involved and learning in the cortex is not purely unsupervised.

Unsupervised learning models have been extended with aspects of reinforcement learning.