Exploring Weight Agnostic Neural Networks


When training a neural network to accomplish a given task, be it image classification or reinforcement learning, one typically refines a set of weights associated with each connection within the network. Another approach to creating successful neural networks that has shown substantial progress is neural architecture search, which constructs neural network architectures out of hand-engineered components such as convolutional network components or transformer blocks. It has been shown that neural network architectures built with these components, such as deep convolutional networks, have strong inductive biases for image processing tasks, and can even perform them when their weights are randomly initialized.



How Digital Detectives Deciphered Stuxnet, the Most Menacing Malware in History

2011-07-11 Kim Zetter

It was January 2010, and investigators with the International Atomic Energy Agency had just completed an inspection at the uranium enrichment plant outside Natanz in central Iran, when they realized that something was off within the cascade rooms where thousands of centrifuges were enriching uranium.