Numerical simulations of Earth's weather and climate require substantial amounts of computation.
Many experts argue that the future of artificial intelligence is limited by the field's ability to integrate symbolic logical reasoning into deep learning architectures.
Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the use of deep networks as cheap "approximate solvers."
Fine-grained classification aims at distinguishing between items with similar global perception and patterns, but that differ by minute details.
The output of a neural network depends on its parameters in a highly nonlinear way, and it is widely assumed that a network's parameters cannot be identified from its outputs.
2 code implementations • 10 Jun 2019 • David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.
The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks.
Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching.
We examine this issue in the context of reinforcement learning, in a setting where an agent is exposed to tasks in a sequence.
To optimize a neural network one often thinks of optimizing its parameters, but it is ultimately a matter of optimizing the function that maps inputs to outputs.
Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology.
no code implementations • 7 Dec 2016 • Yaron Meirovitch, Alexander Matveev, Hayk Saribekyan, David Budden, David Rolnick, Gergely Odor, Seymour Knowles-Barley, Thouis Raymond Jones, Hanspeter Pfister, Jeff William Lichtman, Nir Shavit
The field of connectomics faces unprecedented "big data" challenges.
We show how the success of deep learning could depend not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of practical interest can frequently be approximated through "cheap learning" with exponentially fewer parameters than generic ones.