artificial-intelligence

I have developed a ML model for a classification (0/1) NLP task and deployed it in production environment. The prediction of the model is displayed to users, and the users have the option to give a feedback (if the prediction was right/wrong). How can I continuously incorporate this feedback in my model ? From a UX stand point you dont want a user to correct/teach the system more than twice/thrice for a specific input, system shld learn fast i.e. so the feedback shld be incorporated "fast". (Google priority inbox does this in a seamless way) How does one build this "feedback loop" using which

It always amazed me how the Akinator app could guess a character by asking just several questions. So I wonder what kind of algorithm or method let it do that? Is there a name for that class of algorithms and where can I read more about them? Yes, there is a name for these class of algorithms - it is called classification algorithms in the field of machine learning . Decision trees is one example for classification algorithm. In this classification problem, the features for the algorithm are the answers to the question. Deciding which question should be asked next can be done in various ways -

I'm trying to make a Sudoku Solving program for a couple of days but I'm stuck with the methods. I found this algorithm here but I don't really understand it: start at the first empty cell, and put 1 in it. Check the entire board, and see if there are any conflicts If there are coflicts on the board, increase the number in the current cell by 1 (so change 1 to 2, 2 to 3, etc) If the board is clean move, start at step one again. If all nine possible numbers on a given cell cause a conflict in the board, then you set this cell back to empty, go back to the previous cell, and start again from

How is Q-learning different from value iteration in reinforcement learning? I know Q-learning is model-free and training samples are transitions (s, a, s', r) . But since we know the transitions and the reward for every transition in Q-learning, is it not the same as model-based learning where we know the reward for a state and action pair, and the transitions for every action from a state (be it stochastic or deterministic)? I do not understand the difference. You are 100% right that if we knew the transition probabilities and reward for every transition in Q-learning, it would be pretty

I'm interested in this field,but I'm only familiar with PHP so far. If not,can you recommend a tiny but not so bad project that's easy enough to learn? Take a look to Program O: http://blog.program-o.com/ This is the description of the project: Program O is an AIML engine written in PHP with MySQL. Here you can find support, help, bot addons, a brilliant and friendly community and ofcourse the Program O download files. And this mini tutorial for creating Neural Networks in PHP: http://www.developer.com/lang/php/creating-neural-networks-in-php.html This site could be interesting for you as well

Possible Duplicate: Why is Lisp used for AI? What makes a language suitable for Artificial Intelligence development? I've heard that LISP and Prolog are widely used in this field. What features make them suitable for AI? Cervo Overall I would say the main thing I see about languages "preferred" for AI is that they have high order programming along with many tools for abstraction. It is high order programming (aka functions as first class objects) that tends to be a defining characteristic of most AI languages http://en.wikipedia.org/wiki/Higher-order_programming that I can see. That article is

Can I use batch normalization layer right after input layer and not normalize my data? May I expect to get similar effect/performance? In keras functional it would be something like this: x = Input (...) x = Batchnorm(...)(x) ... Maxim You can do it. But the nice thing about batchnorm, in addition to activation distribution stabilization, is that the mean and std deviation are likely migrate as the network learns. Effectively, setting the batchnorm right after the input layer is a fancy data pre-processing step. It helps, sometimes a lot (e.g. in linear regression). But it's easier and more

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 available for this? Look up AIML (Artificial Intelligence Markup Language), it's been around a number of years and it's pretty well defined and flexible for simple stuff. You can also do pretty sophisticated stuff with all sorts of recursive templates and the results are pretty decent

I'm looking at definitions of the A* path-finding algorithm, and it seems to be defined somewhat differently in different places. The difference is in the action performed when going through the successors of a node, and finding that a successor is on the closed list. One approach (suggested by Wikipedia , and this article ) says: if the successor is on the closed list, just ignore it Another approach (suggested here and here , for example) says: if the successor is on the closed list, examine its cost. If it's higher than the currently computed score, remove the item from the closed list for

In the upcoming version of Photoshop there is a feature called Content-Aware fill. This feature will fill a selection of an image based on the surrounding image - to the point it can generate bushes and clouds while being seamless with the surrounding image. See http://www.youtube.com/watch?v=NH0aEp1oDOI for a preview of the Photoshop feature I'm talking about. My question is: How does this feature work algorithmically? I am a co-author of the PatchMatch paper previously mentioned here, and I led the development of the original Content-Aware Fill feature in Photoshop, along with Ivan Cavero