Giovanni Luca Marchetti
PulseAugur coverage of Giovanni Luca Marchetti — every cluster mentioning Giovanni Luca Marchetti across labs, papers, and developer communities, ranked by signal.
-
New research links neural network critical points to simpler function convergence
Researchers have explored the optimization dynamics of neural networks, focusing on critical points arising from network architecture. Using tools from polynomial algebra and Singular Learning Theory, they analyzed deep…
-
Algebraic Geometry Explores Polynomial Convolutional Networks
A new research paper explores the geometric and optimization properties of polynomial convolutional networks, which utilize monomial activation functions. By applying tools from algebraic geometry, the study analyzes th…
-
New method learns equivariant representations by decomposing latent space
Researchers have developed a novel method for learning representations that are inherently equivariant to data symmetries. This approach decomposes the latent space into components representing intrinsic data classes an…
-
Deep learning mechanics probed via group composition research
Two new research papers explore how neural networks learn structured operations, focusing on a task called sequential group composition. Researchers have analyzed how networks process sequences of group elements to pred…
-
New research explores expressive power of weight-space neural networks
Two new research papers explore the theoretical underpinnings of permutation-equivariant networks, a design crucial for models operating directly on the parameters of other neural networks. The first paper establishes a…