Import AI: Issue 46: Facebook's ImageNet-in-an-hour GPU system, diagnosing networks with attention functions, and the open access paper debate

Attention & interpretability: modern neural networks are hard to interpret because we haven't built tools to make it easy to analyze their decision-making processes. Part of the reason why we haven't built the tools is that it's not entirely obvious how you get a big stack of perceptual math machinery to tell you about what it is thinking in a way that is remotely useful to the untrained eye. The best thing we've been able to come up with, in the case of certain vision and language tasks, is attention where we visualize what parts of a neural network – sometimes down to an individual cell or'neuron' within it – is activating in response to. This can help us diagnose why an AI tool is responding in the way it is. This component is general, working across different neural network architectures (a first, the researchers claim), and only requires the person to fiddle with it at its input or output points.