Inceptionism: Going Deeper into Neural Networks

image calsification, google research, neural networks, feedback, perception, classification, classi

One of the challenges of neural networks is understanding what exactly goes on at each layer. We know that after training, each layer progressively extracts higher and higher-level features of the image, until the final layer essentially makes a decision on what the image shows. For example, the first layer maybe looks for edges or corners. Intermediate layers interpret the basic features to look for overall shapes or components, like a door or a leaf. The final few layers assemble those into complete interpretations–these neurons activate in response to very complex things such as entire buildings or trees. One way to visualize what goes on is to turn the network upside down and ask it to enhance an input image in such a way as to elicit a particular interpretation. Say you want to know what sort of image would result in %E2%80%9CBanana.%E2%80%9D Start with an image full of random noise, then gradually tweak the image towards what the neural net considers a banana

http://googleresearch.blogspot.be/2015/06/inceptionism-going-deeper-into-neural.html

Biotech firm creates fake rhino horn to reduce poaching

synthbio, fabbing, 3d priting, biotech, rhino, superstition, marketing

Pembient, based in San Francisco uses keratin – a type of fibrous protein – and rhino DNA to produce a dried powder which is then 3D printed into synthetic rhino horns which is genetically and spectrographically similar to original rhino horns.The company plans to release a beer brewed with the synthetic horn later this year in the Chinese market. The Chinese and Vietnamese rhino horn craze has caused an unprecedented surge in rhino poaching throughout Africa and Asia bringing the animal to the brink of extinction. In South Africa, home to 80 percent of Africa’s rhino population, 1,215 rhinos were killed in 2014.

http://www.digitaljournal.com/news/environment/biotech-firm-creates-fake-rhino-horn-to-help-save-real-rhinos/article/436325

The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children…

The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children we enjoyed watching clouds and interpreting the random shapes. This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals. But because the data is stored at such a high abstraction, the results are an interesting remix of these learned features.

http://googleresearch.blogspot.be/2015/06/inceptionism-going-deeper-into-neural.html

Instead of exactly prescribing which feature we want the network to amplify, we can also let the network make that decision. In…

Instead of exactly prescribing which feature we want the network to amplify, we can also let the network make that decision. In this case we simply feed the network an arbitrary image or photo and let the network analyze the picture. We then pick a layer and ask the network to enhance whatever it detected. Each layer of the network deals with features at a different level of abstraction, so the complexity of features we generate depends on which layer we choose to enhance. For example, lower layers tend to produce strokes or simple ornament-like patterns, because those layers are sensitive to basic features such as edges and their orientations.

http://googleresearch.blogspot.be/2015/06/inceptionism-going-deeper-into-neural.html

Icelandic magical staves (sigils) are symbols credited with magical effect preserved in various grimoires dating from the 17th…

chaosophia218:

Icelandic magical staves (sigils) are symbols credited with magical effect preserved in various grimoires dating from the 17th century and later. According to the Museum of Icelandic Sorcery and Witchcraft, the effects credited to most of the staves were very relevant to the average Icelanders of the time, who were mostly substitence farmers and had to deal with harsh climatic conditions.

Version control, collaborative editing and undo

eve, programming, versioning, dvcs, editing, collaborative editing, time

Eve is designed for live programming. As the user makes changes, the compiler is constantly re-compiling code and incrementally updating the views. The compiler is designed to be resilient and will compile and run as much of the code as possible in the face of errors. The structural editor restricts partially edited code to small sections, rather than rendering entire files unparseable. The pointer-free relational data model and the timeless views make it feasible to incrementally compute the state of the program, rather than starting from scratch on each edit. We arrived at this design to support live programming but these properties also help with collaborative editing.

http://incidentalcomplexity.com/2015/04/22/version-control/

Visions of transhumanism

transhumanism, life extension, extropy, Paul Graham Raven, libertarianism

The proactionary principle, a creation of first-generation transhumanist figurehead Max More, is an attempt to turn the precautionary principle upon its head. Where the precautionary principle declares that research and experimentation should only be undertaken after a consensus has been reached regarding the low probability of risky outcomes, More’s proactionary principle damns such caution as being detrimental to the advancement of the species, and advocates that research priorities and funding be allocated in accordance with the potential rewards, rather than risks. By suggesting that the State is not only intruding upon one’s freedom to conduct business, but also restricting one’s potential maximal lifespan, More hits upon a two-pronged formula that strikes right at the heart of what it is to be a wealthy western man: the plebeian moonbats don’t just want you to fail, they want you to die before you’re done.

http://thelongandshort.org/issues/season-four/visions-of-transhumanism.html

I have written elsewhere of how much art there is responding to science, but it is much harder to find science that learns…

“I have written elsewhere of how much art there is responding to science, but it is much harder to find science that learns directly from art, since the goals of the two enterprises remain quite different. Or if they both have a similar goal of revealing deeper truths about nature, one does so with amazing insight, the other with rigorously documented investigation. But Domnitch and Gelfand’s work crosses the line sometimes because it reveals natural phenomena scientists thought were impossible to see or even to create. Their best-known work, “Camera Lucida,” investigates the mysterious phenomenon of sonoluminescence, a physical oddity discovered in 1929, whereby tiny oxygen bubbles bombarded with sound can be compressed enough to faintly glow.”

– Rothenberg, David. Survival of the Beautiful: Art, Science, and Evolution. London: Bloomsbury, 2011. (viacarvalhais)

To question what seems so much a matter of course that we’ve forgotten its origins. To rediscover something of the astonishment…

“

To question what seems so much a matter of course that we’ve forgotten its origins. To rediscover something of the astonishment that Jules Verne or his readers may have felt faced with an apparatus capable of reproducing and transporting sounds. For the astonishment existed, along with thousands of others, and it’s they which have moulded us.

What we need to question is bricks, concrete, glass, our table manners, our utensils, our tools, the way we spend our time, our rhythms. To question that which seems to have ceased forever to astonish us. We live, true, we breathe, true; we walk, we open doors, we go down staircases, we sit at a table in order to eat, we lie down on a bed in order to sleep. How? Why? Where? When? Why?

Describe your street. Describe another street. Compare.

Make an inventory of you pockets, of your bag. Ask yourself about the provenance, the use, what will become of each of the objects you take out.

Question your tea spoons.

What is there under your wallpaper?

”

– Georges Perec, The Infra-ordinary, 1971 (vianataliekane)