artificial-intelligence

Higher-order unification

烂漫一生 提交于 2019-11-29 19:51:40
I'm working on a higher-order theorem prover, of which unification seems to be the most difficult subproblem. If Huet's algorithm is still considered state-of-the-art, does anyone have any links to explanations of it that are written to be understood by a programmer rather than a mathematician? Or even any examples of where it works and the usual first-order algorithm doesn't? Charles Stewart State of the art — yes, so far as I know all algorithms more or less take the same shape as Huet's (I follow theory of logic programming, although my expertise is tangential) provided you need full higher

What is the difference between Q-learning and SARSA?

拈花ヽ惹草 提交于 2019-11-29 18:57:05
Although I know that SARSA is on-policy while Q-learning is off-policy, when looking at their formulas it's hard (to me) to see any difference between these two algorithms. According to the book Reinforcement Learning: An Introduction (by Sutton and Barto). In the SARSA algorithm, given a policy, the corresponding action-value function Q (in the state s and action a, at timestep t), i.e. Q(s t , a t ), can be updated as follows Q(s t , a t ) = Q(s t , a t ) + α*(r t + γ*Q(s t+1 , a t+1 ) - Q(s t , a t )) On the other hand, the update step for the Q-learning algorithm is the following Q(s t , a

What's the point of the threshold in a perceptron?

僤鯓⒐⒋嵵緔 提交于 2019-11-29 18:53:22
问题 I'm having trouble seeing what the threshold actually does in a single-layer perceptron. The data is usually separated no matter what the value of the threshold is. It seems a lower threshold divides the data more equally; is this what it is used for? 回答1: Actually, you'll just set threshold when you aren't using bias. Otherwise, the threshold is 0. Remember that, a single neuron divides your input space with a hyperplane. Ok? Now imagine a neuron with 2 inputs X=[x1, x2] , 2 weights W=[w1,

When should I use genetic algorithms as opposed to neural networks? [closed]

蓝咒 提交于 2019-11-29 18:34:42
Is there a rule of thumb (or set of examples) to determine when to use genetic algorithms as opposed to neural networks (and vice-versa) to solve a problem? I know there are cases in which you can have both methods mixed, but I am looking for a high-level comparison between the two methods. From wikipedia: A genetic algorithm (GA) is a search technique used in computing to find exact or approximate solutions to optimization and search problems. and: Neural networks are non-linear statistical data modeling tools. They can be used to model complex relationships between inputs and outputs or to

Any tutorials for developing chatbots? [closed]

≯℡__Kan透↙ 提交于 2019-11-29 18:32:36
As a engineering student, I would like to make a chat bot using python. So, I searched a lot but couldn't really find stuff that would teach me or give me some concrete information to build a intelligent chat bot. I would like to make a chatbot that gives human-like responses (Simply like a friend chatting with you). I am currently expecting it to be as just a software on my laptop (would like to implement in IM, IRC or websites later). So, I am looking for a tutorial/ any other information which would certainly help me to get my project done. Franck Dernoncourt You can read a nice

Weak Classifier

强颜欢笑 提交于 2019-11-29 17:32:35
问题 I am trying to implement an application that uses AdaBoost algorithm. I know that AdaBoost uses set of weak classifiers, but I don't know what these weak classifiers are. Can you explain it to me with an example and tell me if I have to create my own weak classifiers or I'm suppoused to use some kind of algorithm? 回答1: When I used AdaBoost, my weak classifiers were basically thresholds for each data attribute. Those thresholds need to have a performance of more than 50%, if not it would be

Which is the best programming language to write a web bot? [closed]

我只是一个虾纸丫 提交于 2019-11-29 15:18:14
问题 As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance. Closed 9 years ago . I want know which programming language provides good number of libraries to program a web bot? Something like crawling a web page for

Google Deep Dream art: how to pick a layer in a neural network and enhance it

狂风中的少年 提交于 2019-11-29 14:25:05
问题 I am interested in a recent blog post by Google that describes the use of nn to make art. I am particularly interested in one technique: 'In this case we simply feed the network an arbitrary image or photo and let the network analyze the picture. We then pick a layer and ask the network to enhance whatever it detected. Each layer of the network deals with features at a different level of abstraction, so the complexity of features we generate depends on which layer we choose to enhance. For

What is the best data-structure to represent a checkers board when speed is the primary concern?

删除回忆录丶 提交于 2019-11-29 14:06:45
问题 I am currently implementing something quite similar to checkers. So, I have this table game and there are both white and black pieces. Where there are neither white or black pieces, you dno't have pieces. I'm currently doing the GetValidMoves() method that'll return all the current moves one can do with the current board. I am thus wondering what might be the best way to represent the board. The naive approach would be to have a matrix with 0's 1's and 2's (for no piece, white piece and black

Tensor` objects are not iterable when eager execution is not enabled. To iterate over this tensor use `tf.map_fn`

主宰稳场 提交于 2019-11-29 13:38:13
问题 I am trying to create my own loss function: def custom_mse(y_true, y_pred): tmp = 10000000000 a = list(itertools.permutations(y_pred)) for i in range(0, len(a)): t = K.mean(K.square(a[i] - y_true), axis=-1) if t < tmp : tmp = t return tmp It should create permutations of predicted vector, and return the smallest loss. "`Tensor` objects are not iterable when eager execution is not " TypeError: `Tensor` objects are not iterable when eager execution is not enabled. To iterate over this tensor