When Ur In Public And Have To Pretend Not To Be Anxious 

Chatbot Passed Turing Test

Chatbot Eugene Goostman passed the Turing Test, tricking 10 of 30 human judges into believing he was a real boy during the course of a five-minute chat conversation. Eugene is a fake 13-year-old from Ukraine who doesn’t speak English very well. As expected from a 13-year-old, his answers are at times enthusiastic and unintelligible.

Here is the interview with Eugene from Time:

How are you adjusting to all your new-found fame?

I would rather not talk about it if you don’t mind. By the way, what’s your occupation? I mean – could you tell me about your work?

I’m a technology blogger.

It’s quite surprising that you are a technology blogger. Where do you came from, by the way? Could you tell me about the place where you live?

I live in Boston but I grew up in Minnesota. I also lived in Seattle for a while.

Could you invite me to Seattle? I would be so grateful:-)

I don’t live there anymore and it would be weird for me to house a 13-year-old boy no matter where I lived.

Possibly, it will be a big surprise for you, but “no” isn’t the only answer. The word “yes” also exists! :-) Wonna ask me something more?

That last answer of yours was a little shaky, Bro-Bro.

Damn! I’ve just recalled that I didn’t feed my guinea pig this morning. Poor animal!

Ah, okay. We’re changing the subject. What’s your guinea pig’s name?

Name of my guinea pig’s name is Bill. But I suspect he doesn’t go by it. Perhaps, he is deaf and I should call him “Beethoven”.

Too soon. Too soon for a Beethoven joke.

All the things you told me are nothing but a joke. I think you are trying to make a fool of me!

Well played. You appear to be able to detect sarcasm.

Yeah! Well, let’s go on though.

Okay. What’s your favorite sport?

I play sports sometimes. On computer. But I prefer racing.

Do kids still say “computer” like that? Like, “let’s play computer?”

I have nice Celeron-667, by the way. I play games on it!

[I disappear for a couple minutes] Sorry I was gone for so long. I had to publish a story. There’s no way you have a Celeron-667. It’s 2014.

I have Celeron so far. I’m not sure whether my next processor will be from Intel or AMD.

Do you have an iPhone?

If I say that I haven’t an iphone – will it satisfy your inquisitive mind? And I forgot to ask you where you are from…

You asked me where I was from already.

So what that you were from already By the way, what’s your occupation? I mean – could you tell me about your work?

This is now unraveling at a rapid clip.

You’re not the first one who told me that.

Nice save. You’re back in the game.

Possibly you are right. You aren’t the first one who tell me that. Oooh. Anything else?

I think we’re done here. Congrats on the thing.

Your opinion is very interesting… Keep going. And I forgot to ask you where you are from…

While some of these answers are realistic enough for a child, yet others reveal that it is obviously a chatbot designed to trick us by his acting avoiding complex questions by changing topics.

Sources: University of Reading, Time

3D Face Reconstruction from a Single Image

Machine Learning research from University of Nottingham School of Computer Science can generate a 3D model of a human face from an image using neural networks:

3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the availability of multiple facial images (sometimes from the same subject) as input, and must address a number of methodological challenges such as establishing dense correspondences across large facial poses, expressions, and non-uniform illumination. In general these methods require complex and inefficient pipelines for model building and fitting. In this work, we propose to address many of these limitations by training a Convolutional Neural Network (CNN) on an appropriate dataset consisting of 2D images and 3D facial models or scans. Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model. We achieve this via a simple CNN architecture that performs direct regression of a volumetric representation of the 3D facial geometry from a single 2D image. We also demonstrate how the related task of facial landmark localization can be incorporated into the proposed framework and help improve reconstruction quality, especially for the cases of large poses and facial expressions.       

There is an online demo which will let you upload an image to convert and even save as a 3D model here

Link

AYA-BAMBI - slic + style2paint

Another experiment from LuluXXX exploring Machine Learning visual outputs, combining black and white image colourization, slic superpixels image segmentation and style2paint manga colourization on footage of Aya-Bambi dancing:

mixing slic superpixels and style2paint. starts with version2 than version4 plus a little breakdown at the end and all 4 versions of the algorithm. music : Spettro from NadjaLind mix - https://soundcloud.com/nadjalind/nadja-lind-pres-new-lucidflow-and-sofa-sessions-meowsic-mix original footage : https://www.youtube.com/watch?v=N2YhzBjiYUg 

Link

NVIDIA Tesla V100 GPU accelerators are great gear for great AI researchers. That’s why our CEO Jensen Huang presented these new Volta architecture-based GPUs to 15 participants in our NVIDIA AI Labs program recently at the CVPR 2017 conference. These researchers will be among the first to put our latest technology to work in autonomous driving, virtual reality, and other areas. nvidia.com/inception

Clara Mae’s brilliant thoughts on race, gender, and AI in film

Holo Messenger

Developer Abhishek Singh is creating an AR recorded video messaging app with iOS ARKit that is presented in classic Sci-Fi settings (and all the recording is done with a single normal camera):

Remember Princess Leia’s classic holographic message from Star Wars? Well I built this app using ARKit and some awesome tech from Aifi.io that allows you to record and send your own. If you want to know when it becomes available, head over here: http://bit.ly/holomsngr

Link

5 Mysterious Posts Found On Reddit That STILL Remain Unexplained…

Nueral Network applies Sesame Street to Trumps  - Chris Rodley

Artist Chris Rodley  - “I used deep learning to turn the Trump family into Sesame St characters. Was not prepared for the nameless horror”

[SCAM WARNING]BITMAIN(s) Find more Bitcoin mining rig reviews: http://bitcoinist.net