Results (1 - 10 of 27)
- Games: [[PageOutline]] = Games = [[Break]] ---- == Game ...
- ... s, Blind Tic-Tac-Toe || Bridge, Poker, Scrabble || * [[Reminder(todo|Continuous, Embodied - Tabulate in table Above)]] * Snooker * Robocup Soccer [[Break]] [[YouTube(oACt9R9z37U)]] [[Break]] ---- [[YouTube(Jd3-eiid-Uw)]] == Game Algorithms == * [wiki:Algorithm/Search/Adv ...
- — 07/31/09 13:14:49
- Algorithm/Learning/TDL/QLearning: = Q-Learning (Off-Policy TD Control) = One of the most important ...
- ... || ---- == One Step Q-Learning == [[Reminder(todo)]] ---- === References === * [[Reference(RLI)]] === Related === Ancstors ☣ [wiki:Algorithm] ➢ [wiki:Algorithm/Learning] ➢ [wiki:Algorithm/Learning/TDL][[BR]] Siblings ☣ [wiki:Algorithm/Learning/TDL/AHC] ☣ [wiki:Al ...
- — 06/28/09 16:12:39
- Learning/Paradigm/Reinforcement: [[PageOutline]] = Reinforcement Learning Algorithms (AKA Hebbian ...
- ... * Systems must explore the space of actions. [[Reminder(todo|Create a scheme for VS pages, so these blocks can be their own page shared between the LHS & RHS)]] == Applications == [[Quicktime(learning/sims_evolved_virtual_creatures_1994-small.mpg)]] There are many practical appl ...
- — 06/08/09 18:36:03
- Tutorial/Search/AStar: = A* Tutorial = Consider a [wiki:PEAS/Environment/FullyObservable fully ...
- ... [[Reminder(todo|Last question from Week 5 tutorial)]] ---- === References === * [[Reference(AIMA)]] * [http://www.policyalmanac.org/games/aStarTutorial.htm A* Tutorial] === Related === Ancstors ☣ [wiki:Tutorial][[BR]] Other ☣ [ ...
- — 04/21/09 19:45:34
- Learning/Machine/LVQ: = Learning Vector Quantization (LVQ) = ---- == Background == ''Vector ...
- ... [[Reminder(todo|Give an example)]] ---- == LVQ & SOM == In order to use LVQ, a set of approximate reconstruction vectors is first found using the unsupervised SOM algorithm. The supervised LVQ algorithm is then used to fine-tune the ve ...
- — 11/24/08 21:24:23
- Learning/Machine/Committee: [[PageOutline]] = Committee Machines = Committee machines are ...
- ... [[Reminder(todo|Based on what?]] [[Div]] === Bagging & Boosting === See the respecting bagging and boosting pages for details. ---- == Dynamic Structures == In this second class of committee machines, the __input signal is direc ...
- — 11/10/08 22:03:54
- Learning/Machine/Neuron: [[PageOutline]] = The Perceptron (AKA Artificial Neuron) = The ...
- ... ---- == The Biological Neuron == [[Reminder(todo)]] ---- == Three Basic Elements of a Neuron == The neuron has 3 basic elements which can be described as follows... * '''Synapse''' - A set of ''synapses'', or ''connecting links'', each of which is characterized by a ...
- — 11/10/08 18:06:24
- Learning/Machine/SOM: [[PageOutline]] = Kohonen Self Organizing Feature Maps (SOM) = The ...
- ... ==== Competitive Process ==== [[Reminder(todo)]] ==== Cooperative Process ==== [[Reminder(todo)]] ==== Adaptive Phase 1 of 2 - Ordering ==== [[Reminder(todo)]] ==== Adaptive Phase 1 of 2 - Convergence ==== [[Reminder(todo)]] [[SImage(som-flow.png)]] -- ...
- — 11/10/08 17:53:22
- Algorithm/Learning/ModelSelection/Bootstrap: = Bootstrapping = ''Pulling oneself up by one's bootstraps - Efron ...
- ... ---- == Variations == === 0.632 Bootstrap === [[Reminder(todo)]] This method puts more weight on the test observations... [[Div(formula)]] Error = [0.368α + 0.632ε], where ε is the weighted average of errors on the observations omitted from bootstrap samples, and α is the _train ...
- — 11/09/08 11:32:02
- Learning/Machine/SVM: [[PageOutline]] = Support Vector Machines (SVM) = [[Reminder(todo|SVMs ...
- [[PageOutline]] = Support Vector Machines (SVM) = [[Reminder(todo|SVMs do not overfit the data!)]] '''Prerequisites''': It is assumed that the reader is already familiar with certain areas in [wiki:Mathematics/LinearAlgebra linear algebra], ([wiki:Mathematics/LinearAlgebra/Matrices matr ...
- — 11/08/08 22:39:07
Note: See TracSearch
for help on searching.
