artificial-intelligence

问题 Hi got into another roadblock in tensorflow crashcourse...at the representation programming excercises at this page. https://developers.google.com/…/repres…/programming-exercise I'm at Task 2: Make Better Use of Latitude seems I narrowed the issue to when I convert the raw latitude data into "buckets" or ranges which will be represented as 1 or zero in my feature. The actual code and issue I have is in the paste bin. Any advice would be great! thanks! https://pastebin.com/xvV2A9Ac this is to

问题 I am making a chess game in Java and (I think) have successfully implemented Negamax for the AI player. I am having some trouble adding alpha beta pruning to this to improve the algorithm. I have tried following tutorials and example code but just can't get my head around how it works. Below is the code I currently have to get the best move: private Move getBestMove() { System.out.println("Getting best move"); System.out.println("Thinking..."); List<Move> validMoves = generateMoves(true); int

问题 Closed . This question needs to be more focused. It is not currently accepting answers. Want to improve this question? Update the question so it focuses on one problem only by editing this post. Closed 5 years ago . I apologize if this question is a little broad. Hopefully your answers will help me narrow it down to more meaningful questions. I'm experienced in software engineering and had a recent conversation with a friend who suggested that electrical engineering is very software driven

问题 This might be a totally naive question, but i am interested to know the particular reasons. Why was PDDL developed in the first place? Why could we not do the reasoning using First Order Logic? 回答1: Efficiency In Solving Using a more specific language to express your problem makes it possible to apply more specific algorithms to solve them. From a theoretic point of view FOL is undecidable while most flavors of PDDL are still decidable, because PDDL can only express planning problems. And e.g

问题 Maze I have a maze as shown above(use the link) and state 3 contains prize while state 7 contains shock. a mouse can be placed in any state from 1 to 9 randomly and it move through the maze uniformly at random Pi denote the probability that mouse reaches state 3 before state 7, given that AIM started in compartment i. how to compute Pi for ∈ {1,2,3,4,5,6,7,8,9}. 回答1: Let Px be the probability that the game ends in position 3 if it starts in position x . We know that P3=1 and P7=0 If you start

问题 I am trying to run the following tensorflow code and it's working fine the first time. If I try running it again, it keeps throwing an error saying ValueError: Variable layer1/weights1 already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at: File "C:\Users\owner\Anaconda3\envs\DeepLearning_NoGPU\lib\site-packages\tensorflow\python\framework\ops.py", line 1228, in __init__ self._traceback = _extract_stack() File "C:\Users\owner\Anaconda3\envs\DeepLearning

问题 I have been reading this question for reference: Graph Search vs Tree Search One of the commenters made this comment which is exactly the situation I am facing. "It is more formal to say that a 'single state' could be visited multiple times by a tree search, and NOT a node. As every node in search tree corresponds to a single path along the state space graph and is visited at most once by tree searches." My search algorithm is generating nodes that are identical to ones already in the search

问题 I need a good heuristic function for A star for sudoku solving. The sudoku grid is 4X4 and by definition the legal operation from each state is to insert a new number to the next free cell (the order is left to right and up to down). for example, this is the input grid: and we should now fill the cell (1,2). All the nodes are different grids that represents different states. The branching factor is 4, so we have 4 possibilities for the next cell:1, 2, 3 or 4, i.e. 4 children for each node.

问题 In AI, are there any simple and/or very visual examples of how one could implement a genome into a simulation? Basically, I'm after a simple walkthrough (not a tutorial, but rather something of a summarizing nature) which details how to implement a genome which changes the characteristics in an 'individual' in a sumlation. These genes would not be things like: Mass Strength Length, Etc.. But rather they should be the things defining the above things, abstracting the genome from the actual

问题 Could someone please provide some information on how to properly combine a self organizing map with a multilayer perceptron? I recently read some articles about this technique in comparison to regular MLPs and it performed way better in prediction tasks. So, I want to use the SOM as front-end for dimension reduction by clustering the input data and pass the results to an MLP back-end. My current idea of implementing it is it to train the SOM with a couple of training sets and to determine the