Deep Learning
Gaussian Kernel Mixture Network for Single Image Defocus Deblurring
Then, a deep neural network called GKMNet is developed by unrolling a fixed-point iteration of the GKM-based deblurring.
Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory
Available only for the asynchronous leapfrog integrator.
Techniques for Symbol Grounding with SA TNet Sever T opan
Many experts argue that the future of artificial intelligence is limited by the field's
ENS10_Paper_Neurips22
Dataset and all its scripts can be found at https://github.com/spcl/ens10 .
Modern Hopfield Networks and Attention for Immune Repertoire Classification
Michael Widrich, Bernhard Schäfl, Milena Pavlovic, Hubert Ramsauer, Lukas Gruber, Markus Holzleitner, Johannes Brandstetter, Geir Kjetil Sandve, Victor Greiff, Sepp Hochreiter, Günter Klambauer
A central mechanism in machine learning is to identify, store, and recognize patterns. How to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more recent transformer architectures.