• Home
• Up
• Add

] RECOMMENDED READING - ART REVIEW 

neural networks - not many really understand how they work. This is why so many are reluctant to gamble on the mysteries of neural networks

hospital example - worked BUT sent pneumonia+asthma patients home VS to ICU, 

The European Union recently proposed to establish a “right to explanation,” which allows citizens to demand transparency for algorithmic decisions

 The networks are made up of many, sometimes millions, of individual units, called neurons. Each neuron converts many numerical inputs into a single numerical output, which is then passed on to one or more other neurons. As in brains, these neurons are divided into “layers,” groups of cells that take input from the layer below and send their output to the layer above. 

Neural networks are trained by feeding in data, then adjusting the connections between layers until the network’s calculated output matches the known output (which usually consists of categories) as closely as possible. The incredible results of the past few years are thanks to a series of new techniques that make it possible to quickly train deep networks, with many layers between the first input and the final output. One popular deep network called AlexNet is used to categorize photographs—labeling them according to such fine distinctions as whether they contain a Shih Tzu or a Pomeranian. It consists of over 60 million “weights,” each of which tell each neuron how much attention to pay to each of its inputs. “In order to say you have some understanding of the network,” says Jason Yosinski, a computer scientist affiliated with Cornell University and Geometric Intelligence, “you’d have to have some understanding of these 60 million numbers.”

The requirement for interpretability can be seen as another set of constraints, preventing a model from a “pure” solution that pays attention only to the input and output data it is given, and potentially reducing accuracy. 

The result is that modern machine learning offers a choice among oracles: Would we like to know what will happen with high accuracy, or why something will happen, at the expense of accuracy? The “why” helps us strategize, adapt, and know when our model is about to break. The “what” helps us act appropriately in the immediate future.

(neural networks) Deep-learning software attempts to mimic the activity in layers of neurons in the neocortex, the wrinkly 80 percent of the brain where thinking occurs. The software learns, in a very real sense, to recognize patterns in digital representations of sounds, images, and other data.