Search Results for author:
Found 9 papers, 1 papers with code
Do highly over-parameterized neural networks generalize since bad solutions are rare?
We study over-parameterized classifiers where Empirical Risk Minimization (ERM) for learning leads to zero training error.
Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization
We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining.
Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process.
Feature Products Yield Efficient Networks
Such FP-blocks are inspired by models of end-stopped neurons, which are common in cortical areas V1 and especially in V2.
Solving Raven's Progressive Matrices with Multi-Layer Relation Networks
Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans.
Multi-layer Relation Networks
Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture.
Deep Convolutional Neural Networks as Generic Feature Extractors
Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task.
Ranked #30 on
Image Classification
on MNIST
Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks
In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently.
Committees of deep feedforward networks trained with few data
Deep convolutional neural networks are known to give good results on image classification tasks.
Ranked #98 on
Image Classification
on STL-10
