Search Results for author:
Found 14 papers, 6 papers with code
Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning
Our findings indicate that this form of inductive bias can be beneficial in closing the gap between models with local plasticity rules and backpropagation models as well as learning more robust representations in general.
Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation
Identification of cracks is essential to assess the structural integrity of concrete infrastructure.
A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data.
When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics
Although a plethora of architectural variants for deep classification has been introduced over time, recent works have found empirical evidence towards similarities in their training process.
Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference
In this paper we analyze the classification performance of neural network structures without parametric inference.
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning
In this work we critically survey the literature and argue that notable lessons from open set recognition, identifying unknown examples outside of the observed set, and the adjacent field of active learning, querying data to maximize the expected performance gain, are frequently overlooked in the deep learning era.
Fundamental Issues Regarding Uncertainties in Artificial Neural Networks
Artificial Neural Networks (ANNs) implement a specific form of multi-variate extrapolation and will generate an output for any input pattern, even when there is no similar training pattern.
Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?
We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with extreme value theory based open set recognition.
Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge.
Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity.
Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures
We characterize convolutional neural networks with respect to the relative amount of features per layer.
Building effective deep neural networks one feature at a time
Successful training of convolutional neural networks is often associated with suffi- ciently deep architectures composed of high amounts of features.
Building effective deep neural network architectures one feature at a time
Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features.
Model-driven Simulations for Deep Convolutional Neural Networks
The use of simulated virtual environments to train deep convolutional neural networks (CNN) is a currently active practice to reduce the (real)data-hungriness of the deep CNN models, especially in application domains in which large scale real data and/or groundtruth acquisition is difficult or laborious.
