Predicting the accuracy of a neural network prior to training

Constructing a neural network model for each new dataset is the ultimate nightmare for every data scientist. What if you could forecast the accuracy of the neural network earlier thanks to accumulated experience and approximation? ...

Are computer-aided decisions actually fair?

Algorithmic fairness is increasingly important because as more decisions of greater importance are made by computer programs, the potential for harm grows. Today, algorithms are already widely used to determine credit scores, ...

Applying emerging technology to solve environmental challenges

Technology and environmental sustainability leaders must work together on collaborative solutions to unlock the power of emerging technology to address the challenges of environmental sustainability, including those related ...

Using drones to simplify film animation

Producing realistic animated film figures is a highly complex technical endeavour. ETH researchers have now shown how drones can be used to greatly reduce the effort required in the process.

Dual 8-bit breakthroughs bring AI to the edge

This week, at the International Electron Devices Meeting (IEDM) and the Conference on Neural Information Processing Systems (NeurIPS), IBM researchers will showcase new hardware that will take AI further than it's been before: ...

A novel solver for approximate marginal map inference

There is a deep connection between planning and inference, and over the last decade, multiple researchers have introduced explicit reductions showing how stochastic planning can be solved using probabilistic inference with ...

Helping computers to see 3-D structures

If you can recognize structures around you while walking down a city street, you have your eyes to thank. Humans can automatically perceive 3-D structure in the world by identifying lines, shapes, symmetries and the patterns ...

page 12 from 40