That, in a nutshell, is the question addressed by this paper.ĭD is an application of deep learning, or DL. In essence, the DD researcher feeds an image into a multilayer DL network (or utilises a randomly chosen image that is already there), and asks the system to focus on a certain feature, selected either deliberately or at random. The system is next required to modify the image so as to emphasise that feature. This process is then iterated – perhaps very many times. In straightforward DL, multilayer neural networks find patterns on several hierarchical levels (LeCun, Bengio, & Hinton, 2015). The output of one level is used as the input to the one above it, and so on for (sometimes) very many levels. Finally, the last one or two levels are tuned by backprop.Īs a technique for machine learning, DL has already been hugely successful. The DeepMind team, for instance, led by Demis Hassabis and now attached to Google, have used it to learn to play the classic suite of 49 Atari games – in 22 cases, even better than professional game testers (Mnih et al., 2015). The same team later produced a DL system, AlphaGo, that beat the European Go champion 5–0 in October 2015 (Silver et al., 2016), and defeated the world's leading player, Lee Sedol, in March 2016. Since Go has long been recognised as a much more difficult game than chess, it is not surprising that these feats gained huge attention in the media worldwide. And, presumably, soon to be better still. Highly recommended.( DeepMind are currently experimenting with artificial neural networks of over 100 layers.)īut DL suffers from two grave problems. So, if you’d like greater control and faster processing (your gear withstanding) you can either run up the source code (not trivial) or use one of the first commercial offerings Realmac’s Deep Dreamer.Ĭurrently in beta for OS X Yosemite and above, Deep Dreamer provides more control over how the ANN processes an image than most of the online services I’ve tried and not only handles static images but also creates Deep Dream videos! For £9.90 this is a cheap way to explore the world of Deep Dreaming. The problem with most on-line Deep Dream implementations is that you might have to wait for hours for your image to be processed (which is the case with Psychic VR Lab) and there’s not a lot of control over the parameters of the transmogrification (as with Google’s Deep Dream Generator). Here’s one of my photos morphed into a Deep Dream by Google (click to enlarge).ĭeep Dream has also been used to morph videos here’s a clip from the movie “Fear & Loathing in Las Vegas” that’s been processed and it is, quite obviously, really disturbing: If you want to play, er, evaluate this technology there are several Web sites such as Google’s own Deep Dream Generator and Psychic VR Lab that will transmogrify your own images using the Deep Dream software that Google open sourced as an iPython notebook. Many commentators have pointed out that the resulting images have a sort of Hieronymus Bosch feel but that’s very much a result of what Google's ANN had been taught which apparently included lots of dogs (as above) and pagoda-like buildings. It does this operation iteratively and the end results are, to say the least, psychedelic what has been termed by Google’s geeks as "Inceptionalism" (see the main image above). In an attempt to grok how ANNs function Google engineers created Deep Dream, an ANN that, when given an image, looks for things it’s already been taught and inserts them into the image. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning."īut ANNs present researchers and engineers with a problem how they work is next to impossible to understand. Artificial neural networks are generally presented as systems of interconnected "neurons" which exchange messages between each other. "… a family of statistical learning models inspired by biological neural networks (the central nervous systems of animals, in particular the brain) and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. One of the key technologies used to implement deep learning systems is artificial neural networks, or ANNs: "… a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures, with complex structures or otherwise, composed of multiple non-linear transformations." Many of these products rely on an algorithm called "deep learning" which Wikipedia defines as: Artificial intelligence is all the rage these days with AI solutions for everything from scheduling meetings to Big Data mining in gastronomy appearing at an unprecedented rate.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |