Shan Carter, a researcher at Google Brain, recently visited his daughter’s second-grade class with an unusual payload: an array of psychedelic pictures, filled with indistinct shapes and warped pinwheels of color. He passed them around the class, and was delighted when the students quickly deemed one of the blobs a dog ear. A group of 7-year-olds had just deciphered the inner visions of a neural network. Carter is among the researchers trying to pierce the “black box” of deep learning. Neural networks have proven tremendously successful at tasks like identifying objects in images, but how they do so remains largely a mystery. Their inner workings are shielded from human eyes, buried in layers of computations, making it hard to diagnose errors or biases. On Wednesday, Carter’s team released a new paper that offers a peek inside, showing how a neural network builds and arranges visual concepts. This particular line of research dates back to 2015, when … [Read more...] about Shark or Baseball? Inside the ‘Black Box’ of a Neural Network
Learning neural networks
A.I. is everywhere at the moment, and it’s responsible for everything from the virtual assistants on our smartphones to the self-driving cars soon to be filling our roads to the cutting-edge image recognition systems reported on by yours truly. Unless you’ve been living under a rock for the past decade, there’s good a chance you’ve heard of it before — and probably even used it. Right now, artificial intelligence is to Silicon Valley what One Direction is to 13-year-old girls: an omnipresent source of obsession to throw all your cash at, while daydreaming about getting married whenever Harry Styles is finally ready to settle down. (Okay, so we’re still working on the analogy!) But what exactly is A.I.? — and can terms like “machine learning,” “artificial neural networks,” “artificial intelligence” and “Zayn Malik” (we’re still working on that analogy…) be used … [Read more...] about Machine learning? Neural networks? Here’s your guide to the many flavors of A.I.
September 10, 2018 - Written By Daniel Fuller A new simulator simply called Evolution, which is available in a desktop browser and on the Play Store, uses a neural network to bring to life any creatures you can think to cobble together from an assortment of joints, bones and muscles that you can place wherever and link however you see fit. The creatures all spawn and learn across multiple generations, with two specimens chosen per generation to pass on their genes. No two simulations will ever be the same thanks to the wiles of the random mating, The created species will try their hands at three tasks to determine their fitness score; walking, jumping, and climbing stairs.The simulation is actually pretty simple on the surface, despite the complex neural networking and artificial intelligence operations happening just beneath. All you have to do is tap or click where you want to place joints, connect those using bones, then link the bones with muscles. Muscles can expand and … [Read more...] about Evolution Simulator Is Driven By A Neural Network
Neural networks have a reputation for being computationally expensive. But only the training portion of things really stresses most computer hardware, since it involves regular evaluations of performance and constant trips back and forth to memory to tweak the connections among its artificial neurons. Using a trained neural network, in contrast, is a much simpler process, one that isn't nearly as computationally complex. In fact, the training and execution stages can be performed on completely different hardware. And there seems to be a fair bit of flexibility in the hardware that can be used for either of these two processes. For example, it's possible to train neural networks using a specialized form of memory called a memristor or execute trained neural networks using custom silicon chips. Now, researchers at UCLA have done something a bit more radical. After training a neural network using traditional computing hardware, they 3D printed a set of panels that manipulated light in a … [Read more...] about Neural network implemented with light instead of electrons
An open-source battle is being waged for the soul of artificial intelligence. It is being fought by industry titans, universities and communities of machine-learning researchers world-wide. This article chronicles one small skirmish in that fight: a standardized file format for neural networks. At stake is the open exchange of data among a multitude of tools instead of competing monolithic frameworks. The good news is that the battleground is Free and Open. None of the big players are pushing closed-source solutions. Whether it is Keras and Tensorflow backed by Google, MXNet by Apache endorsed by Amazon, or Caffe2 or PyTorch supported by Facebook, all solutions are open-source software. Unfortunately, while these projects are open, they are not interoperable. Each framework constitutes a complete stack that until recently could not interface in any way with any other framework. A new industry-backed standard, the Open Neural Network Exchange format, could change that. Now, … [Read more...] about ONNX: the Open Neural Network Exchange Format