Tag Info

21

I study artificial intelligence in a masters program, and we use neural networks quite a lot. They are actually quite useful. I think the problem for neural nets are their name. This both confuses what a neural network actual is, and makes some people question their merits because they expect them to act like brains, when they are really a fancy type of ...

13

A neural network is a class of computing system. They are created from very simple processing nodes formed into a network. They are inspired by the way that biological systems such as the brain work, albeit many orders of magnitude less complex at the moment. They are fundamentally pattern recognition systems and tend to be more useful for tasks which can ...

13

Genetic Algorithms and Neural Networks are not suitable here. They are meta-heuristics for finding a good-enough, approximate solution to a problem. Notably, both require you to find a cost function to rate candidate solutions. Once you have such a cost function, it might be easier to manually come up with an algorithm that optimizes for this cost. This is ...

11

You can use simulated annealing. I did something like that before I landed my first job - see https://vimeo.com/20610875 (demo starting at 2:50, algorithm explained from 6:15). Simulated annealing is a type of a genetic algorithm, and maybe it was not suitable in theory (as @amon maintains in his answer), but it worked very well in practice, and it was ...

7

Work in binary: 0, 1, 10, 11, 100, 101... Know your math: 0+0=00, 0+1=01, 1+0=01, 1+1=10 Know your logic: or, and, not, xor... Find that the low bit is a XOR and the high bit is a AND. Expand the principle of one bit to 8, 16, 32, 64 bits Build it with logic gates. If you want to know more, see my answer to How is fundamental mathematics efficiently ...

6

Genetics Algorithms do apply here. During my undergraduate program, one of my colleagues wrote a paper to very similar problem of yours. You can look for Job Shop Scheduling and also Open Shop Scheduling or Flow Shop Scheduling can be interesting starting points To use a genetic algorithm you don't need a perfect solution, you can start with N random ...

6

If the data is linearly separable then yes, it's possible. Take one of these scatter plots which show the blue points and the red points and the line between them. (image stolen from here) If your neural network got the line right, it is possible it can have a 100% accuracy. Remember that a neuron's output (before it goes through an activation function) ...

5

Depends heavily on how you are trying to make the prediction. Most PRNGs that I've used usually operate on a ring of numbers within a finite range. The seed decides what number you start on, and you progress around the ring one number at a time. The order of the numbers appears random, but their order is actually very deterministic. For example, lets say ...

4

The practical uses of a neural network is pretty much everything. Recognition / detection in vision Artificial intelligence in games Classification ... In short : neural network can do pretty much everything as long you're able to get enough data and some efficient machine to get the right parameters. My professor told me once that some competition ...

3

The crucial part of the story is this: Currently, I am in the process of building a crowd sourced platform for people who are knowledgeable to go in and mark up compatibility between those parts as its not always clear cut if they are for example: And this... Now what I want is an AI to be able to learn from the decisions of the ...

3

If the random number generator is reasonably good, it is impossible to predict the Nth number given only the prior N-1 numbers. Any random number generator that is used for cryptographic purposes, for example, will be sufficiently random that you won't be able to predict the next number. If you've got a poor random number generation, on the other hand, it ...

3

Thad Starner (now at GA Tech) was able to get this to work with HMMs and a cap-mounted video camera back in 1995. I imagine you'll have some good luck along those lines with the massive increase in processing power and sensors since then. Thad Starner and Alex Pentland. Real-time american sign language recognition from video using hidden markov models. In ...

2

I know some ASL (?) has been captured and recognised by computers in the past, and that was a while ago. I remember watching videos of this on VHS. 1994 at the latest. Sign Languages (there's more than one) are typically multi-channel media — it's not just the handshapes, so the gloves may not be quite enough (depending on your aims). My ASL is almost non-...

2

Well, I haven't built too many AI systems before, but let's take a naive crack at this. If I were going to use a neural network for this, the assigned tags to new parts would be the input nodes, the (vast) list of items it could be compatible with would the the output nodes, and the hidden layer would be it's user-confirmed compatibilities or ...

2

NNs are often used for tasks where we're unsure about what "features" are important. I can recognize a handwritten "2" but it's difficult to describe the essence of a "2" given the enormous variation in hand writing. In your case, the important features of your items seem to be decided by the tags. Humans have already done the hard work. Similarly NNs are ...

2

Have a Look in ada boost (adaptative booster). The idea is to use independent weak classifier (your detectors) and combine them in a clever way. It roughly goes like this: It first tries to evaluate the different detectors to detect and use an optimal linear combination of them to classify the data. It then tries to find another combination able to provide ...

2

It sounds like this would be suitable for a neural network, probably a standard feedforward type. I'm not sure how much you know about neural networks, but FYI the 'rules' it discovers won't be in a human-readable format. So if you want to run images through it and sort them, it'll do that; but if you're aiming to get a list of rules that you can see, you'...

2

"Hidden" nodes aren't really hidden like a black box - it is just a layer in between your input and output nodes. You program will have the values of all weights and the signal values propagated through the neural network. Once you have the output error, you can use all that information with the "archaic" (do you mean arcane?) mathematics. I found this ...

2

Question 1: Is my above understanding of the process correct? Yes; for the feed-forward process. It should be noted that the process can be computed with a matrix multiply for each layer. Question 2: Is this correct? Should the output values be a direct result of the sigmoid function? Yes, you generally apply the activation function to output layer. ...

2

What you are looking for is Neuro Evolution. According to this paper you could be in a position to create a trainable feed forward Neural Network (some extra information might also be found here). My recommendation would be to start small, maybe first start by making your character move and stop in the presence of danger. Neural networks can be rather ...

2

It is a mathematical scheme for building a equation (taking multiple numerical inputs and providing a single numerical output) with adjustable coefficients weights. There are algorithms that can adjust the coefficients to make the equation approximate the expected outputs, given a training set consisting of inputs and expected outputs. The simplest example, ...

2

Randomizing the nodes and connections, increases the initial entropy of the network. Creating stronger biases in the network at the beginning (before training), would presumably facilitate the formation of some of the neural paths faster. When all other factors are equal for an input, this will amortize worst cases during training (this should happen ...

2

The first approach is called supervised learning, and the second is called reinforcement learning. There are two ways you can use a neural network with reinforcement learning for chess: as a policy network or as a value network: a policy network would decide which move to play, whereas a value network would just evaluate the utility of a board position and ...

1

It sounds like you are using * (elementwise multiplication) when you really want to be using mmul (matrix multiplication). If you are computing a length 4 hidden layer from a length 1 input vector, then your weight matrix should be a 4x1 matrix, e.g.: (def weights [[1.0] [2.0] [3.0] [4.0]]) ;; a 4x1 weight matrix (def input [1.5]) (mmul weights input) =>...

1

When you train a neural network, you need both positive and negative inputs. If you were to say, only indicate to a neural network that when given an image that it should return 1, when given an image which is not similar, it may return 1 all the same. And in this circumstance, while there is only 1 image you'd like other images to be similar to, there ...

1

Context two-layer neuronal networks and svms do linear classification = splitting good vectors into bad vectors by putting a line or flat layer between them which has one dimension less than the vector space. (line in 2d space; dot onto line). When you have three layer neuronal networks they can classify the XOR (in a,b out a xor b). So you can classify ...

1

Unless I misunderstand the problem (which could be stated more clearly IMO), you absolutely do not want to order entities by distance. It is critical that each input to the neural network denotes the same physical entity throughout - or else nothing will make sense. You need to specify your problem more precisely, and devise your network inputs accordingly. ...

1

If I understand you correctly, you essentially have a data set (crowd-)sourced from actual people, which describes the compatibility between various parts. You would like to build something which analyses this information, and figures out the associations between the parts and the compatibility flag. Essentially, extracting this type of information from a ...

1

This is a perfect application for a full-text indexer such as Lucene. Let's say your questionnaire asks about three things: smoking, diabetes and obesity. Once the text of the articles is indexed, you can use the answers you get to form queries that will return the most relevant articles first. So, for example, the query for an overweight, non-diabetic ...

1

Why not just tack a machine ID on top of the service identifier? That way you have 31 unique keys, which specify both the service and machine, and you're left with a lookup into 10000. Also, I don't really understand your math. From what I see, it looks more like: You're choosing from (200 machines) * (10 services per machine) * (10000 values per service). ...

Only top voted, non community-wiki answers of a minimum length are eligible