Note: this answer was correct at the time it was made, but has since become outdated. It is rare to have more than two hidden layers in a neural network. The number of layers will usually not be a parameter of your network you will worry much about. Although multi-layer neural networks with many layers … Read more
Much of the work in the field of neuroevolution involves using neural networks with continuous inputs and outputs. There are several common approaches: One node per value Linear activation functions – as others have noted, you can use non-sigmoid activation functions on output nodes if you are concerned about the limited range of sigmoid functions. … Read more
Good feature engineering involves two components. The first is an understanding the properties of the task you’re trying to solve and how they might interact with the strengths and limitations of the classifier you’re using. The second is experimental work where you will be testing your expectations and find out what actually works and what … Read more
The first step, in taking this game to the next level, is … …to have a very clear view of prior art! (and pardon me to say, the question doesn’t suggest that you have such an extensive insight into the matter [and you’re not alone, count me in ;-)]) Even, and maybe in particular, if … Read more
I’ll try to keep this short and sweet. One approach that is often used to solve these problems in simulation is a Rapidly-Exploring Random Tree. To give at least a little credibility to my post, I’ll admit I studied these, and motion planning was my research lab’s area of expertise (probabilistic motion planning). The canonical … Read more
“AI engine” can mean an awful lot of different things. What kind of “AI” are you looking for? Here is a list of some machine learning software. Many of them are open source (the linked page shows the licenses).
There are two parts to this question. The first part is “what is the form of function learned by these methods?” For NN and SVM this is typically the same. For example, a single hidden layer neural network uses exactly the same form of model as an SVM. That is: Given an input vector x, … Read more
Once a NN has been trained, for eg. using backprogation as mentioned in the question (whereby the backprogation logic has “nudged” the weights in ways that minimize the error function) the weights associated with all individual inputs (“outside” inputs or intra-NN inputs) are fixed. The NN can then be used for classifying purposes. Whereby the … Read more
All the cool bearded gurus in what’s left of AI research use Lisp 🙂 There are two big camps: Common Lisp and Scheme. They have different syntax, etc. Lots of good stuff written for both. Java is a very popular all-purpose language but a lot of the interesting stuff in AI / Functional Programming, such … Read more
I built an evolutionary algorithm for retail inventory replenishment in a product targeted at huge plant nurseries (and there are some really big, smart ones — $200m companies). It was probably the coolest thing I’ve ever worked on. Using three years of historical data, it crunched and evolved for a week straight while I was … Read more