Deep Visualization with the Caffe Framework

University of Wyoming’s Evolving Artificial Intelligence Laboratory have been using the power of NVIDIA Tesla GPUs to accelerate their research since 2012. The Lab, which focuses on evolving artificial intelligence with a major focus on large-scale, structurally organized neural networks, has garnered press from some of the largest media outlets, including BBC, National Geographic, NBC News, The Atlantic and featured on the cover of Nature in May 2015.

ie_16_good_looking_horizontal
Images produced by an Innovation Engine that look like example target classes. In each pair, an evolved image (left) is shown with a real image (right) from the training set used to train the deep neural network that evaluates evolving images.

Jeff Clune, Assistant Professor, Computer Science Department and Director of the Evolving Artificial Intelligence Laboratory, recently talked about his lab’s work using the Caffe deep learning framework, and how they are harnessing the power of Tesla GPUs to accelerate the research on visualizing deep neural networks.

“The speedups GPUs provide for training deep neural networks are well-documented and allow us to train models in a week that would otherwise take months,” said Clune. “And algorithms continuously improve. Recently, NVIDIA’s cuDNN technology allowed us to speed up our training time by an extra 20% or so.”

The following video shows off work from the Evolving AI Lab on visualizing deep neural networks.

Read the interview on Parallel Forall >>