recentpopularlog in

robertogreco : neuralnetworks   7

Eyeo 2017 - Robin Sloan on Vimeo
"Robin Sloan at Eyeo 2017
| Writing with the Machine |

Language models built with recurrent neural networks are advancing the state of the art on what feels like a weekly basis; off-the-shelf code is capable of astonishing mimicry and composition. What happens, though, when we take those models off the command line and put them into an interactive writing environment? In this talk Robin presents demos of several tools, including one presented here for the first time. He discusses motivations and process, shares some technical tips, proposes a course for the future — and along the way, write at least one short story together with the audience: all of us, and the machine."
robinsloan  writing  howwewrite  neuralnetworks  computing  eyeo  eyeo2017  2017 
september 2017 by robertogreco
Eyes Without a Face — Real Life
"The American painter and sculptor Ellsworth Kelly — remembered mainly for his contributions to minimalism, Color Field, and Hard-edge painting — was also a prodigious birdwatcher. “I’ve always been a colorist, I think,” he said in 2013. “I started when I was very young, being a birdwatcher, fascinated by the bird colors.” In the introduction to his monograph, published by Phaidon shortly before his death in 2015, he writes, “I remember vividly the first time I saw a Redstart, a small black bird with a few very bright red marks … I believe my early interest in nature taught me how to ‘see.’”

Vladimir Nabokov, the world’s most famous lepidopterist, classified, described, and named multiple butterfly species, reproducing their anatomy and characteristics in thousands of drawings and letters. “Few things have I known in the way of emotion or appetite, ambition or achievement, that could surpass in richness and strength the excitement of entomological exploration,” he wrote. Tom Bradley suggests that Nabokov suffered from the same “referential mania” as the afflicted son in his story “Signs and Symbols,” imagining that “everything happening around him is a veiled reference to his personality and existence” (as evidenced by Nabokov’s own “entomological erudition” and the influence of a most major input: “After reading Gogol,” he once wrote, “one’s eyes become Gogolized. One is apt to see bits of his world in the most unexpected places”).

For me, a kind of referential mania of things unnamed began with fabric swatches culled from Alibaba and fine suiting websites, with their wonderfully zoomed images that give you a sense of a particular material’s grain or flow. The sumptuous decadence of velvets and velours that suggest the gloved armatures of state power, and their botanical analogue, mosses and plant lichens. Industrial materials too: the seductive artifice of Gore-Tex and other thermo-regulating meshes, weather-palimpsested blue tarpaulins and piney green garden netting (winningly known as “shade cloth”). What began as an urge to collect colors and textures, to collect moods, quickly expanded into the delicious world of carnivorous plants and bugs — mantises exhibit a particularly pleasing biomimicry — and deep-sea aphotic creatures, which rewardingly incorporate a further dimension of movement. Walls suggest piled textiles, and plastics the murky translucence of jellyfish, and in every bag of steaming city garbage I now smell a corpse flower.

“The most pleasurable thing in the world, for me,” wrote Kelly, “is to see something and then translate how I see it.” I feel the same way, dosed with a healthy fear of cliché or redundancy. Why would you describe a new executive order as violent when you could compare it to the callous brutality of the peacock shrimp obliterating a crab, or call a dress “blue” when it could be cobalt, indigo, cerulean? Or ivory, alabaster, mayonnaise?

We might call this impulse building visual acuity, or simply learning how to see, the seeing that John Berger describes as preceding even words, and then again as completely renewed after he underwent the “minor miracle” of cataract surgery: “Your eyes begin to re-remember first times,” he wrote in the illustrated Cataract, “…details — the exact gray of the sky in a certain direction, the way a knuckle creases when a hand is relaxed, the slope of a green field on the far side of a house, such details reassume a forgotten significance.” We might also consider it as training our own visual recognition algorithms and taking note of visual or affective relationships between images: building up our datasets. For myself, I forget people’s faces with ease but never seem to forget an image I have seen on the internet.

At some level, this training is no different from Facebook’s algorithm learning based on the images we upload. Unlike Google, which relies on humans solving CAPTCHAs to help train its AI, Facebook’s automatic generation of alt tags pays dividends in speed as well as privacy. Still, the accessibility context in which the tags are deployed limits what the machines currently tell us about what they see: Facebook’s researchers are trying to “understand and mitigate the cost of algorithmic failures,” according to the aforementioned white paper, as when, for example, humans were misidentified as gorillas and blind users were led to then comment inappropriately. “To address these issues,” the paper states, “we designed our system to show only object tags with very high confidence.” “People smiling” is less ambiguous and more anodyne than happy people, or people crying.

So there is a gap between what the algorithm sees (analyzes) and says (populates an image’s alt text with). Even though it might only be authorized to tell us that a picture is taken outside, then, it’s fair to assume that computer vision is training itself to distinguish gesture, or the various colors and textures of the slope of a green field. A tag of “sky” today might be “cloudy with a threat of rain” by next year. But machine vision has the potential to do more than merely to confirm what humans see. It is learning to see something different that doesn’t reproduce human biases and uncover emotional timbres that are machinic. On Facebook’s platforms (including Instagram, Messenger, and WhatsApp) alone, over two billion images are shared every day: the monolith’s referential mania looks more like fact than delusion."
2017  rahelaima  algorithms  facebook  ai  artificialintelligence  machinelearning  tagging  machinevision  at  ellsworthkelly  color  tombrdley  google  captchas  matthewplummerfernandez  julesolitski  neuralnetworks  eliezeryudkowsky  seeing 
may 2017 by robertogreco
Image-to-Image Demo - Affine Layer
"Recently, I made a Tensorflow port of pix2pix by Isola et al., covered in the article Image-to-Image Translation in Tensorflow. I've taken a few pre-trained models and made an interactive web thing for trying them out. Chrome is recommended.

The pix2pix model works by training on pairs of images such as building facade labels to building facades, and then attempts to generate the corresponding output image from any input image you give it. The idea is straight from the pix2pix paper, which is a good read."

[See also: https://phillipi.github.io/pix2pix/

"We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without hand-engineering our loss functions either."



"Here we show comprehensive results from each experiment in our paper. Please see the paper for details on these experiments.

Effect of the objective
Cityscapes
Facades

Effect of the generator architecture
Cityscapes

Effect of the discriminator patch scale
Cityscapes
Facades

Additional results
Map to aerial
Aerial to map
Semantic segmentation
Day to night
Edges to handbags
Edges to shoes
Sketches to handbags
Sketches to shoes"]
machinelearning  art  drawing  via:meetar  deeplearning  neuralnetworks 
february 2017 by robertogreco
A Neural Network Playground
"Tinker With a Neural Network Right Here in Your Browser.
Don’t Worry, You Can’t Break It. We Promise.

Um, What Is a Neural Network?

It’s a technique for building a computer program that learns from data. It is based very loosely on how we think the human brain works. First, a collection of software “neurons” are created and connected together, allowing them to send messages to each other. Next, the network is asked to solve a problem, which it attempts to do over and over, each time strengthening the connections that lead to success and diminishing those that lead to failure. For a more detailed introduction to neural networks, Michael Nielsen’s Neural Networks and Deep Learning is a good place to start. For more a more technical overview, try Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.

This Is Cool, Can I Repurpose It?

Please do! We’ve open sourced it on GitHub with the hope that it can make neural networks a little more accessible and easier to learn. You’re free to use it in any way that follows our Apache License. And if you have any suggestions for additions or changes, please let us know.

We’ve also provided some controls below to enable you tailor the playground to a specific topic or lesson. Just choose which features you’d like to be visible below then save this link, or refresh the page.

Show test data
Discretize output
Play button
Learning rate
Activation
Regularization
Regularization rate
Problem type
Which dataset
Ratio train data
Noise level
Batch size
# of hidden layers
What Do All the Colors Mean?

Orange and blue are used throughout the visualization in slightly different ways, but in general orange shows negative values while blue shows positive values.

The data points (represented by small circles) are initially colored orange or blue, which correspond to positive one and negative one.

In the hidden layers, the lines are colored by the weights of the connections between neurons. Blue shows a positive weight, which means the network is using that output of the neuron as given. An orange line shows that the network is assiging a negative weight.

In the output layer, the dots are colored orange or blue depending on their original values. The background color shows what the network is predicting for a particular area. The intensity of the color shows how confident that prediction is.

Credits

This was created by Daniel Smilkov and Shan Carter. This is a continuation of many people’s previous work — most notably Andrej Karpathy’s convnet.js and Chris Olah’s articles about neural networks. Many thanks also to D. Sculley for help with the original idea and to Fernanda Viégas and Martin Wattenberg and the rest of the Big Picture and Google Brain teams for feedback and guidance."
neuralnetworks  data  computing  deeplearning  ai  danielsmilkov  shancarter 
april 2016 by robertogreco
Random Radicals: A Fake Kanji Experiment
[via:
http://prostheticknowledge.tumblr.com/post/136754440176/random-radicals-continuation-of-project-by
"As humans, we are able to communicate with others by drawing pictures, and somehow this has evolved into modern language. The ability to express our thoughts is a very powerful tool in our society. Being able to write is generally more difficult than just being able to read, and this is especially true for the Chinese language. From personal experience, being able to write Chinese is a lot more difficult than just being able to read Chinese and requires a greater understanding of the language.

We now have machines that can help us accurately classify images and read handwritten characters. However, for machines to gain a deeper understanding of the content they are processing, they will also need to be able to generate such content. The next natural step is to have machines draw simple pictures of what they are thinking about, and develop an ability to express themselves. Seeing how machines produce drawings may also provide us with some insights into their learning process.

In this work, we have trained a machine to learn Chinese characters by exposing it to a Kanji database. The machine learns by trying to form invariant patterns of the shapes and strokes that it sees, rather than recording exactly what it sees into memory, kind of like how our own brains work. Afterwards, using its neural connections, the machine attempts to write something out, stroke-by-stroke, onto the screen."]

[See also: http://blog.otoro.net/2015/12/28/recurrent-net-dreams-up-fake-chinese-characters-in-vector-format-with-tensorflow/
via: http://prostheticknowledge.tumblr.com/post/136134267951/recurrent-net-dreams-up-fake-chinese-characters

"… I think a more interesting task is to generate data, which I view as an extension to classifying data. Like how being able to write a Chinese character demonstrate more understanding than merely knowing how to read that character, I think being able to generate content is also key to understanding that content. Being able generate a picture of a 22 year old attractive lady is much more impressive than merely being able to estimate that the this woman is likely around 22 years of age.

An example of a generative task is the translation machines developed to translate English into another language in real time. Generative art and music has been increasingly popular. Recently, there has been work on using techniques such as generative adversarial networks (GANs) to generate bitmap pictures of fake images that look like real ones, like fake cats, fake faces, fake bedrooms and even fake anime characters, and to me, those problems are a lot more exciting to work on, and a natural extension to classification problems."]

[See also: http://www.genekogan.com/works/a-book-from-the-sky.html
via: http://prostheticknowledge.tumblr.com/post/136157512956/a-book-from-the-sky-%E5%A4%A9%E4%B9%A6-another-neural-network

"A Book from the Sky 天书

Another Neural Network Chinese character project - this one by Gene Kogan which generates new Kanji from a handwritten dataset:

These images were created by a deep convolutional generative adversarial network (DCGAN) trained on a database of handwritten Chinese characters, made with code by Alec Radford based on the paper by Radford, Luke Metz, and Soumith Chintala in November 2015.

The title is a reference to the 1988 book by Xu Bing, who composed thousands of fictitious glyphs in the style of traditional Mandarin prints of the Song and Ming dynasties.

A DCGAN is a type of convolutional neural network which is capable of learning an abstract representation of a collection of images. It achieves this via competition between a “generator” which fabricates fake images and a “discriminator” which tries to discern if the generator’s images are authentic (more details). After training, the generator can be used to convincingly generate samples reminiscent of the originals.

… a DCGAN is trained on a labeled subset of ~1M handwritten simplified Chinese characters, after which the generator is able to produce fake images of characters not found in the original dataset."]
art  deeplearning  kanji  chinese  machinelearning  neuralnetworks 
january 2016 by robertogreco
Matt Webb – What comes after mobile « Mobile Monday Amsterdam
"Matt Webb talks about how slightly smart things have invaded our lives over the past years. People have been talking about artificial intelligence for years but the promise has never really come through. Matt shows how the AI promise has transformed and now seems to be coming to us in the form of simple toys instead of complex machines. But this talks is about much more then AI, Matt also introduces chatty interfaces & hard math for trivial things."

[via: http://preoccupations.tumblr.com/post/1157711285/what-comes-after-mobile-matt-webb ]
mattwebb  berg  berglondon  future  mobile  technology  ai  design  productinvention  invention  spacebinding  timebinding  energybinding  spimes  internetofthings  anybot  ubicomp  glowcaps  geography  context  privacy  glanceableuse  cloud  embedded  chernofffaces  understanding  math  mathematics  augmentedreality  redlaser  neuralnetworks  mechanicalturk  shownar  toys  lanyrd  iot  ar 
september 2010 by robertogreco
Self-organizing map - Wikipedia
"A self-organizing map (SOM) or self-organizing feature map (SOFM) is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional (typically two-dimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different from other artificial neural networks in the sense that they use a neighborhood function to preserve the topological properties of the input space."
maps  mathematics  networks  optimization  datamining  database  clustering  classification  algorithms  ai  learning  programming  research  statistics  visualization  neuralnetworks  mapping  som  self-organizingmaps 
june 2010 by robertogreco

Copy this bookmark:





to read