Search Results for author:
Found 6 papers, 0 papers with code
Enabling Uncertainty Estimation in Iterative Neural Networks
Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance.
DEBOSH: Deep Bayesian Shape Optimization
Graph Neural Networks (GNNs) can predict the performance of an industrial design quickly and accurately and be used to optimize its shape effectively.
HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation
Deep implicit surfaces excel at modeling generic shapes but do not always capture the regularities present in manufactured objects, which is something simple geometric primitives are particularly good at.
Scaling up deep neural networks: a capacity allocation perspective
Following the recent work on capacity allocation, we formulate the conjecture that the shattering problem in deep neural networks can only be avoided if the capacity propagation through layers has a non-degenerate continuous limit when the number of layers tends to infinity.
Capacity allocation through neural network layers
In the highly non-linear limit where decoupling is total, we show that the propagation of capacity throughout the layers follows a simple markovian rule, which turns into a diffusion PDE in the limit of deep networks with residual layers.
Capacity allocation analysis of neural networks: A tool for principled architecture design
We focus more particularly on spatial capacity allocation, which analyzes a posteriori the effective number of parameters that a given model has allocated for modelling dependencies on a given point or region in the input space, in linear settings.
