In this keynote address, Perceive CEO Steve Teig will discuss how deep learning’s reliance on inefficient models based on recipes and anecdotes, rather than scientific principles and explanatory mathematics, leads to unsustainable compromises in power-efficiency, privacy, and user experience. By focusing instead on using information theory to guide the development of more rigorous, scalable machine learning, we could create models that are more predictive, power-efficient and cost-effective.

More Videos

[AI Compute Symposium] Machine learning for real: Thinking more carefully about efficiency, loss functions, and GANs

Deep learning seems to touch every discipline these days, but behind its startling magic tricks, it is surprisingly primitive. It is concerning to note the extent to which today’s deep learning relies on folklore: on recipes and anecdotes, rather than on scientific principles and explanatory mathematics. Think of how much more trustworthy, robust, compact, and power-efficient our models would be if we designed them more rigorously. My assertions will be accompanied by some motivating (and occasionally humorous) examples.

For more information, please visit the AI Compute Symposium website here.

More Events