Search Results for author:
Found 12 papers, 4 papers with code
DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes.
Landscape of Neural Architecture Search across sensors: how much do they differ ?
With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable.
A Data-driven Approach to Neural Architecture Search Initialization
First, we perform a calibrated clustering analysis of the search space, and second, we extract the centroids and use them to initialize a NAS algorithm.
Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems
In this paper, we propose to use fitness landscape analysis to study a neural architecture search problem.
Lessons from the Clustering Analysis of a Search Space: A Centroid-based Approach to Initializing NAS
In this study, we propose to accelerate a NAS algorithm using a data-driven initialization technique, leveraging the availability of NAS benchmarks.
Reliable and Fast Recurrent Neural Network Architecture Optimization
This article introduces Random Error Sampling-based Neuroevolution (RESN), a novel automatic method to optimize recurrent neural network architectures.
Bayesian Neural Architecture Search using A Training-Free Performance Metric
Recurrent neural networks (RNNs) are a powerful approach for time series prediction.
JSDoop and TensorFlow.js: Volunteer Distributed Web Browser-Based Neural Network Training
Then, volunteers access the web page of the problem and start processing the tasks in their web browsers.
Random Error Sampling-based Recurrent Neural Network Architecture Optimization
Our findings show that we can achieve state-of-the-art error performance and that we reduce by half the time needed to perform the optimization.
DLOPT: Deep Learning Optimization Library
Deep learning hyper-parameter optimization is a tough task.
Low-Cost Recurrent Neural Network Expected Performance Evaluation
In this study, we propose a low computational cost model to evaluate the expected performance of a given architecture based on the distribution of the error of random samples of the weights.
