Search Results for author:
Found 21 papers, 9 papers with code
Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion
In recent years, we have seen many advancements in wood species identification.
Hyperdimensional computing: a fast, robust and interpretable paradigm for biological data
Advances in bioinformatics are primarily due to new algorithms for processing diverse biological data sources.
Prediction of Activated Sludge Settling Characteristics from Microscopy Images with Deep Convolutional Neural Networks and Transfer Learning
Activated sludge settling characteristics, for example, are affected by microbial community composition, varying by changes in operating conditions and influent characteristics of wastewater treatment plants (WWTPs).
The Hyperdimensional Transform for Distributional Modelling, Regression and Classification
Hyperdimensional computing (HDC) is an increasingly popular computing paradigm with immense potential for future intelligent applications.
The Hyperdimensional Transform: a Holographic Representation of Functions
We introduce the hyperdimensional transform as a new kind of integral transform.
Heteroskedastic conformal regression
Conformal prediction, and split conformal prediction as a specific implementation, offer a distribution-free approach to estimating prediction intervals with statistical guarantees.
RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps
Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied.
Ranked #1 on
Image Classification
on DTD
(using extra training data)
Hyperparameter optimization in deep multi-target prediction
As a result of the ever increasing complexity of configuring and fine-tuning machine learning models, the field of automated machine learning (AutoML) has emerged over the past decade.
Improving Deep Neural Network Random Initialization Through Neuronal Rewiring
In this sense, PA rewiring only reorganizes connections, while preserving the magnitude and distribution of the weights.
Valid prediction intervals for regression problems
Over the last few decades, various methods have been proposed for estimating prediction intervals in regression settings, including Bayesian methods, ensemble methods, direct interval estimation methods and conformal prediction methods.
Multi-target prediction for dummies using two-branch neural networks
In this work we present a generic deep learning methodology that can be used for a wide range of multi-target prediction problems.
Incorporating Unmodeled Dynamics Into First-Principles Models Through Machine Learning
The machine learning model fills in the knowledge gaps of the first-principles model, capturing the unmodeled dynamics and thus improving the representativeness of the model.
A Comparative Study of Pairwise Learning Methods based on Kernel Ridge Regression
Problems of that kind are often referred to as pairwise learning, dyadic prediction or network inference problems.
Blob Reconstruction Using Unilateral Second Order Gaussian Kernels With Application to High-ISO Long-Exposure Image Denoising
Blob detection and image denoising are fundamental, and sometimes related, tasks in computer vision.
Exact and efficient top-K inference for multi-target prediction by querying separable linear relational models
Many complex multi-target prediction problems that concern large target spaces are characterised by a need for efficient prediction strategies that avoid the computation of predictions for all targets explicitly.
Efficient Pairwise Learning Using Kernel Ridge Regression: an Exact Two-Step Method
In this work we analyze kernel-based methods for pairwise learning, with a particular focus on a recently-suggested two-step method.
An evolutionary approach to the identification of Cellular Automata based on partial observations
In this paper we consider the identification problem of Cellular Automata (CAs).
Improved texture image classification through the use of a corrosion-inspired cellular automaton
In addition, in order to verify the robustness of the method, its invariance to noise and rotation were tested.
A two-step learning approach for solving full and almost full cold start problems in dyadic prediction
Dyadic prediction methods operate on pairs of objects (dyads), aiming to infer labels for out-of-sample dyads.
Identification of functionally related enzymes by learning-to-rank methods
For a given query, the search operation results in a ranking of the enzymes in the database, from very similar to dissimilar enzymes, while information about the biological function of annotated database enzymes is ignored.
Efficient Regularized Least-Squares Algorithms for Conditional Ranking on Relational Data
In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object.
