artificial-intelligence

ReLU not learning to handle negative inputs Keras / Tensorflow

五迷三道 提交于 2019-12-12 17:35:29
问题 I want my neural network to convert a negative value into a positive value. Theoretically this can be done using a ReLU function and 1 node which learns the input weight to be -1 (so a negative input is multiplied by -1 = positive input. It just keeps on outputting 0. Code below. I used -1 as input values to see if it could learn on at least a single input. I tried adding more layers but it doesn't help see edit, IT DID help if I add more train_input = np.asarray([[-1]]*10000) # Input arr of

Train neural network with sine function

断了今生、忘了曾经 提交于 2019-12-12 17:27:31
问题 I want to train a neural network with the sine() function. Currently I use this code and the (cerebrum gem): require 'cerebrum' input = Array.new 300.times do |i| inputH = Hash.new inputH[:input]=[i] sinus = Math::sin(i) inputH[:output] = [sinus] input.push(inputH) end network = Cerebrum.new network.train(input, { error_threshold: 0.00005, iterations: 40000, log: true, log_period: 1000, learning_rate: 0.3 }) res = Array.new 300.times do |i| result = network.run([i]) res.push(result[0]) end

Missing values for the data to be used in a Neural Network model for prediction

≡放荡痞女 提交于 2019-12-12 16:48:40
问题 I currently have a lot of data that will be used to train a prediction neural network (gigabytes of weather data for major airports around the US). I have data for almost every day, but some airports have missing values in their data. For example, an airport might not have existed before 1995, so I have no data before then for that specific location. Also, some are missing whole years (one might span from 1990 to 2011, missing 2003). What can I do to train with these missing values without

Merge weights of same model trained on 2 different computers using tensorflow

荒凉一梦 提交于 2019-12-12 16:18:42
问题 I was doing some research on training deep neural networks using tensorflow. I know how to train a model. My problem is i have to train the same model on 2 different computers with different datasets. Then save the model weights. Later i have to merge the 2 model weight files somehow. I have no idea how to merge them. Is there a function that does this or should the weights be averaged? Any help on this problem would be useful Thanks in advance 回答1: It is better to merge weight updates

AI of spaceship's propulsion: control the force to land a ship at x=0 and v=0

亡梦爱人 提交于 2019-12-12 13:43:55
问题 I have to code AI to control many propulsion jets for a spaceship in a game. For simplicity :- Let the space be 1D. Spaceship is a point and there is only 1 jet. Rule and problem Let x , v and a are position, velocity, acceleration of the spaceship. Let F be the force of jet that apply to the ship. I know mass m of the spaceship, let's say m =1. Here is a summary :- acceleration = F/m; v = vOld + acceleration*timestep; x = xOld + v*timestep; The objective is to land the ship on a certain

AI library framework in Ada

不羁的心 提交于 2019-12-12 09:50:59
问题 I'm looking for an Ada constructed framework for AI. I think Ada would be perfect for implementing temporal and stochastic paradigms due to its tasking and real-time mechanisms, but did not find anyone who tried to make such a libraries. Actually I did not find strong implementations on other languages too. For C# I found http://www.c-sharpcorner.com/1/56/, and for C++ I found http://mind.sourceforge.net/cpp.html but both did not get much popularity. Maybe java has good AI libraries too, but

how to begin neural network programming [closed]

一个人想着一个人 提交于 2019-12-12 08:32:04
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 7 years ago . i am quite a novice in the field of neural networks . I have read some theory regarding neural networks. Now i want to do some real

check if a name seems “human”?

柔情痞子 提交于 2019-12-12 08:26:39
问题 I have an online RPG game which I'm taking seriously. Lately I've been having problem with users making bogus characters with bogus names, just a bunch of different letters. Like Ghytjrhfsdjfnsdms, Yiiiedawdmnwe, Hhhhhhhhhhejejekk. I force them to change names but it's becoming too much. What can I do about this? Could I somehow check so at least you can't use more than 2 of the same letter beside each other?? And also maybe if it contains vowels 回答1: I would recommend concentrating your

C# Pathing algorithm for moving a object from point(X, Y) to point(X, Y)

久未见 提交于 2019-12-12 06:28:25
问题 Given a object which may move forward, backward, left and right at a given X,Y point. How to efficiently direct the object to a X,Y point using the given movement mechanics in the most efficient and human natural way. The object is available for movement in real time, you may tell them to "startMoving|Direction|()" and "stopMoving|Direction|()". Though as a additional twist and the part I am having trouble with, is the facing of the object is never known, only its current location is known,

at least one grammar must be loaded before doing a recognition

心已入冬 提交于 2019-12-12 04:32:07
问题 Hello i try to create simple AI program , so i define two grammar and load them and i get this error at least one grammar must be loaded before doing a recognition. the error from visual studio is : An exception of type 'System.InvalidOperationException' occurred in System.Speech.dll but was not handled in user code Additional information: At least one grammar must be loaded before doing a recognition. here is the code this is the class class DefineGrammar { /// <summary> /// Define Choices /