2

Basically what you are looking for was developed as Sikuli by the Sikuli Lab at the University of Colorado Boulder and is now maintained and further developed as SikuliX by RaiMan and the open source community. It is free, gratis & open source (MIT Licenced) and provides: Search the Desktop visually for specific components & events Interact with ...


2

here are a couple resources I have found, that provide an open source "dialog system". https://github.com/superscriptjs/superscript (Javascript) I just ran this yesterday locally, with the telnet interface for rules it looks interesting. There is an example using websockets; but I didn't get that working as of yet. https://github.com/plison/opendial (...


2

My goto for any natural language work is NLTK which in its own words is: NLTK is a leading platform for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources such as WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, ...


1

SoundHound is an app I have used for years that makes a playlist for you on Spotify and there’s no charge. Find it in the App Store! It works great...very few songs are not recognized and it will even keep the song recorded that it can’t find and you can run it through at a later date. It’s also available for Android devices so it’s great for those who use ...


1

If you are a data scientist, iris looks interesting: https://github.com/Ejhfast/iris-agent It is a domain specific conversational agent used to perform common tasks and calculations in the field of data science. Also, if you're a programmer, do some research and start buidling your own neural networks. There are some good tensorflow tutorials out there, for ...


1

You can use a combination of OpenCV (to get the image and perform initial processing of it to do things like text localisation) and possibly OCR (e.g. Tesseract) to convert the text to any format that you desire. I would recommend using python as the glue to stick all of these together and to output to CSV (it has a library for that of course). There are ...


1

We decided to use (maybe it helps someone): Flutter + Unity 3D + AR Foundation + flutter_unity_widget Flutter - nice multiplatform experience Unity 3D & AR Foundation - enough AR and Image Tracking functionality flutter_unity_widget - to merge together aforementioned technologies


1

I did some work on code from Michael Heilmann and Noah H. Smith which attempts to tackle this issue (question generation from text), and can be used as starting point for further research: https://github.com/kutschkem/SmithHeilmann_fork/tree/master/SmithHeilmann This is from around 2010, so 10 years old. There has probably been more research since then, ...


1

Python is rapidly rising in the ranks to become one of the most popular programming languages. It's very versatile. Java is another great language to learn because it is still used basically everywhere. However, the choice of which programming language to use is really up to you. For example, if you're a great C programmer but not that experienced in the ...


1

Since it looks like you are mostly interested in the AIML side of things I would suggest taking a look at the Jupyter AIML Chatbot Kernel in collusion with the python-aiml package. This solution is: Open Source Self Hosted Runs On Linux (or OS-X or Windows) Python rather than Java Ready to go Easy to install Installation: pip install juptyer pip install ...


1

I would recommend using MATLAB for this kind of analysis. The documentation in MATLAB is superb, and they already have tutorials for doing just this sort of thing. MATLAB also allows you to do transfer learning, so you can take an already existing deep neural network and fine tune its weights in order to make your model applicable to your use case without ...


1

You should find some useful information in the article at https://autottblog.wordpress.com/programming-the-car/opencv/ which links to a repo. Also for anything OpenCV and Deep Learning I strongly recommend reading Adrians blog at pyimagesearch as it gives you a really good grounding in both.


1

There is Wolfram Alpha. This is essentially a search engine with significant internal intelligence. It has an API and can be embedded in web pages. Its output can be textual or graphical. Furthermore, there are apps for phones & tablets to interact with the knowledge base. You have tagged your question gratis. The API is free for "personal and ...


1

I've found TypingAid which describes itself as TypingAid is a simple, compact, and handy auto-completion utility. It is customizable enough to be useful for regular typing and for programming. It just seems like autocomplete for english rather than anything sophisticated though. There's certainly a lack of desktop level AI developments right now.


1

There is a template language called Spintax. If you operate a website or handle email spam, you may have seen it in action. The idea is: you provide a sentence template providing several options to choose from. The generator has a built-in randomizer and generates different sentences each time. A short example that is used for spam: I {couldn’t|could not} ...


1

I am not familiar with Deep Belief Networks, but it looks like the word has evolved a little since this question was asked, and I found three alternatives are more or less relevant answers: In Matlab: See DeepLearnToolbox In Java: See Deeplearning4j or H20 Deep Learning See Looking for a convenient way to call Java from C++ for bridging the gap from C++ to ...


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