The two products Gamalon released show that this technique could have near-term commercial use. Image credits: Gamalon/MIT Technology Review Therefore, even if you draw a figure that's different from what the app has previously seen, as long as it recognizes certain features - like how a square with a triangle on top is probably a house - it will make a correct prediction. However, unlike Google's version, which relied on sketches it had previously seen to make predictions, Gamalon's app relies on probabilistic programming to identify an object's key features. The app is similar to one released by Google last year in that it predicts what a person is trying to sketch. Gamalon CEO and cofounder Ben Vigoda showed MIT Technology Reviewa demo drawing app that uses their new method. “It has the potential to take care of the difficult parts automatically.” “Probabilistic programming will make machine learning much easier for researchers and practitioners,” explained Brendan Lake, an NYU research fellow who worked on a probabilistic programming technique in 2015. While this new approach to programming still has difficult challenges to overcome, it has significant potential to automate the development of machine-learning algorithms. The program also refines its knowledge as further examples are provided, and its code can be rewritten to tweak the probabilities. This form of probabilistic programming - a code that uses probabilities instead of specific variables - requires fewer examples to make a determination, such as, for example, that the sky is blue with patches of white clouds. The Bayesian probability is used to refine predictions about the world using experience. It is based on a mathematical framework named after 18 th century mathematician Thomas Bayes. Gamalon calls the technique it employed Bayesian program synthesis. For instance, could the same results be obtained by exposing deep-learning AI to fewer examples? Boston-based startup Gamalon developed a new technology to try to answer just that, and this week, it released two products that utilize its new approach. Complex work can be accomplished using this method, but it certainly leaves something to be desired.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |