4 resultados para Regulation devices and piloting learning
em Massachusetts Institute of Technology
Resumo:
Babies are born with simple manipulation capabilities such as reflexes to perceived stimuli. Initial discoveries by babies are accidental until they become coordinated and curious enough to actively investigate their surroundings. This thesis explores the development of such primitive learning systems using an embodied light-weight hand with three fingers and a thumb. It is self-contained having four motors and 36 exteroceptor and proprioceptor sensors controlled by an on-palm microcontroller. Primitive manipulation is learned from sensory inputs using competitive learning, back-propagation algorithm and reinforcement learning strategies. This hand will be used for a humanoid being developed at the MIT Artificial Intelligence Laboratory.
Resumo:
There has been recent interest in using temporal difference learning methods to attack problems of prediction and control. While these algorithms have been brought to bear on many problems, they remain poorly understood. It is the purpose of this thesis to further explore these algorithms, presenting a framework for viewing them and raising a number of practical issues and exploring those issues in the context of several case studies. This includes applying the TD(lambda) algorithm to: 1) learning to play tic-tac-toe from the outcome of self-play and of play against a perfectly-playing opponent and 2) learning simple one-dimensional segmentation tasks.
Resumo:
Sigmoid type belief networks, a class of probabilistic neural networks, provide a natural framework for compactly representing probabilistic information in a variety of unsupervised and supervised learning problems. Often the parameters used in these networks need to be learned from examples. Unfortunately, estimating the parameters via exact probabilistic calculations (i.e, the EM-algorithm) is intractable even for networks with fairly small numbers of hidden units. We propose to avoid the infeasibility of the E step by bounding likelihoods instead of computing them exactly. We introduce extended and complementary representations for these networks and show that the estimation of the network parameters can be made fast (reduced to quadratic optimization) by performing the estimation in either of the alternative domains. The complementary networks can be used for continuous density estimation as well.
Resumo:
The photoviscosity effect in aqueous solutions of novel poly(4-methacryloyloxyazobenzene-co-N,N-dimethyl acrylamide) (MOAB-DMA) was demonstrated. The observed significant reduction in the zero-shear viscosity upon UV-irradiation of MOAB-DMA aqueous solutions was due to the dissociation of the interchain azobenzene aggregates. Such phenomena can be advantageously used in photoswitchable fluidic devices and in protein separation. Introduction of enzymatically degradable azo cross-links into Pluronic-PAA microgels allowed for control of swelling due to degradation of the cross-links by azoreductases from the rat intestinal cecum. Dynamic changes in the cross-link density of stimuli-responsive microgels enable novel opportunities for the control of gel swelling, of importance for drug delivery and microgel sensoric applications.