Combining neural networks with symbolic representations might make them more versatile and dependable.
Don Monroe
Advertisement
A Deeper Understanding of Deep Learning
Kernel methods clarify why neural networks generalize so well.
Errors and biases in artificial intelligence systems often reflect the data used to train them.
Two-dimensional materials — graphene and its cousins — could enable better integrated circuits.
Formulating a decades-old geometric conjecture as a satisfiability problem opened the door to its final resolution.
The Power of Quantum Complexity
A theorem about computations that exploit quantum mechanics challenges longstanding ideas in mathematics and physics.
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get Involved