Profile cover photo
Profile photo
André Haynes
153 followers
153 followers
About
André's interests
View all
André's posts

Post has attachment

Post has attachment

Post has attachment

Post has attachment

Post has shared content
A new way to train neural networks so that they provide not only predictions and classifications but rationales for their decisions has been developed.

"One of the data sets on which the researchers tested their system is a group of reviews from a website where users evaluate different beers. The data set includes the raw text of the reviews and the corresponding ratings, using a five-star system, on each of three attributes: aroma, palate, and appearance."

"What makes the data attractive to natural-language-processing researchers is that it's also been annotated by hand, to indicate which sentences in the reviews correspond to which scores. For example, a review might consist of eight or nine sentences, and the annotator might have highlighted those that refer to the beer's 'tan-colored head about half an inch thick,' 'signature Guinness smells,' and 'lack of carbonation.' Each sentence is correlated with a different attribute rating."

"As such, the data set provides an excellent test of the CSAIL researchers' system. If the first module has extracted those three phrases, and the second module has correlated them with the correct ratings, then the system has identified the same basis for judgment that the human annotator did."

Post has attachment

Post has shared content
A Beautiful and Intricate Shape

If you roll a circle inside one 3 times its size, it will actually trace out a 4 pointed star shape called an Astroid (this shape is traced out in the animation in orange). But what if inside the smaller circle, there is an even smaller one tracing out a smaller Astroid?
This animation shows the intricate shape that is generated by adding the effects of all the Astroids.

► Creation from Matt Henderson>> http://bit.ly/2dPUXzk

► Are you interested in the code? Take a look here>> http://bit.ly/2e9moYj

► What is an Astroid?>> http://bit.ly/2e9nenG


#Mathematics, #Astroid, #GeometricCurves, #Geometry, #Animations
Animated Photo

Post has shared content
"Brain waves can be used to detect potentially harmful personal information." Brain wave analysis from electroencephalogram (EEG) machines have been proposed as authentication devices. "However, those brain waves can tell more about a person than just his or her identity. It could reveal medical, behavioral or emotional aspects of a person that, if brought to light, could be embarrassing or damaging to that person. And with EEG devices becoming much more affordable, accurate and portable and applications being designed that allows people to more readily read an EEG scan, the likelihood of that happening is dangerously high."

"The EEG has become a commodity application. For $100 you can buy an EEG device that fits on your head just like a pair of headphones. Now there are apps on the market, brain-sensing apps where you can buy the gadget, download the app on your phone and begin to interact with the app using your brain signals."

Post has shared content
Microsoft CEO Satya Nadella on artificial intelligence, algorithmic accountability, and what he learned from Tay. "Let's take image recognition. If our image recognition API by itself had some bias, because of lack of data or the way the feature selection happened or the way we set up the convolutional neural network that we designed, I fully think we've got to be accountable, like bugs we are accountable for. Because after all, for all of our talk of AI, ultimately human engineers are defining the parameters in which AI works."

"One of my biggest learnings from [chatbot] Tay was that you need to build even AI that is resilient to attacks. [...] Just like you build software today that is resilient to a DDOS attack, you need to be able to be resilient to a corpus attack, that tries to pollute the corpus so that you pick up the wrong thing in your AI learners."

Post has shared content
A paper explaining how Aging.AI, the algorithm developed by Insilico that is supposed to be able to guess your age based on your biomarkers works has been published by a journal, and it's open access so you can read it on line, if you're curious how the system works. Basically it's a deep neural network trained on 60,000 blood samples with 21 data points.
Wait while more posts are being loaded