artificial-intelligence

问题 Okay, let me preface this by saying that I am well aware that this depends on MANY factors, I'm looking for some general guidelines from people with experience. My goal is not to make a Neural Net that can compute squares of numbers for me, but I thought it would be a good experiment to see if I implemented the Backpropagation algorithm correctly. Does this seem like a good idea? Anyways, I am worried that I have not implemented the learning algorithm (fully) correctly. My Testing (Results):

问题 Okay, let me preface this by saying that I am well aware that this depends on MANY factors, I'm looking for some general guidelines from people with experience. My goal is not to make a Neural Net that can compute squares of numbers for me, but I thought it would be a good experiment to see if I implemented the Backpropagation algorithm correctly. Does this seem like a good idea? Anyways, I am worried that I have not implemented the learning algorithm (fully) correctly. My Testing (Results):

问题 I Know general issues include local maxima and plateaus however I am curious if there is any more issues associated to this specific search and what my best course of action would be in order to overcome these issues. Can someone also give me an example of which sort of problem this search would be good to use for? 回答1: Problems with best first search: It is greedy. In many cases it leads to a very quick solution (because your number of developed nodes does not increase exponentially, it is

问题 This question ought to be real simple. But the documentation isn't helping. I am using R. I must use the neuralnet package for a multinomial classification problem. All examples are for binomial or linear output. I could do some one-vs-all implementation using binomial output. But I believe I should be able to do this by having 3 units as the output layer, where each is a binomial (ie. probability of that being the correct output). No? This is what I would using nnet (which I believe is doing

问题 Is the greedy best-first search algorithm different from the best-first search algorithm? The wiki page has a separate paragraph about Greedy BFS but it's a little unclear. My understanding is that Greedy BFS is just BFS where the "best node from OPEN" in wikipedia's algorithm is a heuristic function one calculates for a node. So implementing this: OPEN = [initial state] CLOSED = [] while OPEN is not empty do 1. Remove the best node from OPEN, call it n, add it to CLOSED. 2. If n is the goal

问题 Closed. This question is off-topic. It is not currently accepting answers. Want to improve this question? Update the question so it's on-topic for Stack Overflow. Closed 4 years ago . What I want to do is build a simple bot which sends me a set of information stored in database to my messanger chat window [Chatting services are gTalk, Yahoo and other commonly used chating products] Also, it should be capable of accepting few predefined commands and replying them. Is there any opensource code

问题 I am working on a project based on the facial recognition and verification. I am using Siamese network to get the 128 vector of the face ( Embeddings ). I am storing the encodings/embeddings of the person's face in the database and then checking or say matching the incoming face's encodings with the previously stored encodings to recognize the person. To make a robust system, I have to store more than one encodings of the same person. When I have used only a single encoding vector, and

问题 I am implementing a NxN puzzle solver using A* search algorithm and using Manhattan distance as a heuristic and I've run into a curious bug (?) which I can't wrap my head around. Consider these puzzles (0 element being blank space): (initial) 1 0 2 7 5 4 8 6 3 (goal) 1 2 3 4 5 6 7 8 0 The minumum number of moves to reach solution from initial state is 11. However, my solver, reaches goal in 17 moves. And therein lies the problem - my puzzle solver mostly solves the solvable puzzles in a

问题 My project is Face Authentication. System Description: My input is only one image (which was taken when the user logins for the first time) and using that image system should authenticate whenever the user logins to the application. The authentication images may differ from the first input image like -- different illumination conditions, different distance from camera and -10 to 10 degrees variation in pose. The camera used is same (ex: ipad) for all cases. 1) Authentication images are stored

问题 I've written a domain and a test problem in PDDL, but apparently the graphplan implementation can't find a plan. Here's the domain: (define (domain aperture) (:requirements :strips :typing :negative-preconditions) (:types cube hallway room - location ) (:predicates (at ?l - location) (has ?c - cube) (connected ?l1 - location ?l2 - location) (in ?c - cube ?l - location) ) (:action enter :parameters (?h - hallway ?r - room) :precondition (and (connected ?h ?r) (connected ?r ?h) (at ?h) (not (at