Search Results for author:
Found 30 papers, 13 papers with code
Using Part-based Representations for Explainable Deep Reinforcement Learning
In this paper, we propose a non-negative training approach for actor models in RL, enabling the extraction of part-based representations that enhance interpretability while adhering to non-negative constraints.
UAV Active Perception and Motion Control for Improving Navigation Using Low-Cost Sensors
In this study a model pipeline is proposed that combines computer vision with control-theoretic methods and utilizes low cost sensors.
Deep Active Perception for Object Detection using Navigation Proposals
Despite the significant potential of active perception, it poses several challenges, primarily involving significant changes in training pipelines for deep learning models.
Non-negative isomorphic neural networks for photonic neuromorphic accelerators
To this end, we introduce a methodology to obtain the non-negative isomorphic equivalents of regular neural networks that meet requirements of neuromorphic hardware, overcoming the aforementioned limitations.
Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Management
Financial portfolio management describes the task of distributing funds and conducting trading operations on a set of financial assets, such as stocks, index funds, foreign exchange or cryptocurrencies, aiming to maximize the profit while minimizing the loss incurred by said operations.
Multiplicative update rules for accelerating deep learning training and increasing robustness
We claim that the proposed framework accelerates training, while leading to more robust models in contrast to traditionally used additive update rule and we experimentally demonstrate their effectiveness in a wide range of task and optimization methods.
Deep Learning for Energy Time-Series Analysis and Forecasting
Energy time-series analysis describes the process of analyzing past energy observations and possibly external factors so as to predict the future.
Variational Voxel Pseudo Image Tracking
Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its predictions to the decision method or a human supervisor.
A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields
In this paper we evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the training set, as well as propose methods to alleviate such phenomena based on the available annotations from the target domain.
MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
The final of the 4 provided datasets contained real noise from the O3a observing run and signals up to a duration of 20 seconds with the inclusion of precession effects and higher order modes.
VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT).
Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
In several cases, small improvements can be observed, but the most significant improvement still comes from the addition of a second network that models the residual error.
Quadratic mutual information regularization in real-time deep CNN models
In this paper, regularized lightweight deep convolutional neural network models, capable of effectively operating in real-time on devices with restricted computational power for high-resolution video input are proposed.
Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation
Knowledge Distillation has been established as a highly promising approach for training compact and faster models by transferring knowledge from heavyweight and powerful models.
Semantic Scene Segmentation for Robotics Applications
Semantic scene segmentation plays a critical role in a wide range of robotics applications, e. g., autonomous navigation.
Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
Based on this finding, we design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients.
Attention-based Neural Bag-of-Features Learning for Sequence Data
In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information for the given learning objective.
Heterogeneous Knowledge Distillation using Information Flow Modeling
The proposed method is capable of overcoming the aforementioned limitations by using an appropriate supervision scheme during the different phases of the training process, as well as by designing and training an appropriate auxiliary teacher model that acts as a proxy model capable of "explaining" the way the teacher works to the student.
Bag of Color Features For Color Constancy
To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention.
Deep Adaptive Input Normalization for Time Series Forecasting
Deep Learning (DL) models can be used to tackle time series analysis tasks with great success.
Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data
However, combining existing BoF formulations with deep feature extractors pose significant challenges: the distribution of the input features is not stationary, tuning the hyper-parameters of the model can be especially difficult and the normalizations involved in the BoF model can cause significant instabilities during the training process.
Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval
The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI).
Style Decomposition for Improved Neural Style Transfer
Universal Neural Style Transfer (NST) methods are capable of performing style transfer of arbitrary styles in a style-agnostic manner via feature transforms in (almost) real-time.
Interactive dimensionality reduction using similarity projections
In order to visualize that data in 2D or 3D, usually Dimensionality Reduction (DR) techniques are employed.
Decoding Generic Visual Representations From Human Brain Activity using Machine Learning
Among the most impressive recent applications of neural decoding is the visual representation decoding, where the category of an object that a subject either sees or imagines is inferred by observing his/her brain activity.
Using Deep Learning for price prediction by exploiting stationary limit order book features
The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems.
Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data
Forecasting the movements of stock prices is one the most challenging problems in financial markets analysis.
Learning Deep Representations with Probabilistic Knowledge Transfer
Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one.
Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks.
Dimensionality Reduction using Similarity-induced Embeddings
The vast majority of Dimensionality Reduction (DR) techniques rely on second-order statistics to define their optimization objective.
