Search Results for author:
Found 25 papers, 14 papers with code
Revisiting the Robustness of the Minimum Error Entropy Criterion: A Transfer Learning Case Study
In this paper, we revisit the robustness of the minimum error entropy (MEE) criterion, a widely used objective in statistical signal processing to deal with non-Gaussian noises, and investigate its feasibility and usefulness in real-life transfer learning regression tasks, where distributional shifts are common.
Multivariate Time Series Early Classification Across Channel and Time Dimensions
Nowadays, the deployment of deep learning models on edge devices for addressing real-world classification problems is becoming more prevalent.
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data.
Improving generalization in reinforcement learning through forked agents
An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments.
Disentangled (Un)Controllable Features
In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space.
An Empirical Evaluation of Multivariate Time Series Classification with Input Transformation across Different Dimensions
We also show that if we keep the transformation method constant, there is a statistically significant difference in accuracy results when applying it across different dimensions, with accuracy differences ranging from 0. 23 to 47. 79 percentage points.
Towards a General Purpose CNN for Long Range Dependencies in $N$D
The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework.
Improving generalization to new environments and removing catastrophic forgetting in Reinforcement Learning by using an eco-system of agents
Adapting a Reinforcement Learning (RL) agent to an unseen environment is a difficult task due to typical over-fitting on the training environment.
Taking ROCKET on an Efficiency Mission: Multivariate Time Series Classification with LightWaveS
We show that we achieve speedup ranging from 9x to 53x compared to ROCKET during inference on an edge device, on datasets with comparable accuracy.
The Dutch Draw: Constructing a Universal Baseline for Binary Prediction Models
Summarizing, the DD baseline is: (1) general, as it is applicable to all binary classification problems; (2) simple, as it is quickly determined without training or parameter-tuning; (3) informative, as insightful conclusions can be drawn from the results.
Transfer-Learning Across Datasets with Different Input Dimensions: An Algorithm and Analysis for the Linear Regression Case
On the other hand, combining these new inputs with historical data remains a challenge that has not yet been studied in enough detail.
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost.
Taking ROCKET on an efficiency mission: A distributed solution for fast and accurate multivariate time series classification
Specifically, utilizing a wavelet scattering transformation of the time series and distributed feature selection, we manage to create a solution which employs just 2, 5% of the ROCKET features, while achieving accuracy comparable to recent deep learning solutions.
Jasmine: A New Active Learning Approach to Combat Cybercrime
These approaches choose speci? fic unlabeled instances by a query function that are expected to improve overall classi? cation performance.
A Framework for Imbalanced Time-series Forecasting
Time-series forecasting plays an important role in many domains.
pH-RL: A personalization architecture to bring reinforcement learning to health practice
We implemented our open-source RL architecture and integrated it with the MoodBuster mobile application for mental health to provide messages to increase daily adherence to the online therapeutic modules.
CKConv: Continuous Kernel Convolution For Sequential Data
Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori.
Ranked #5 on
Sequential Image Classification
on Sequential MNIST
Mixing Consistent Deep Clustering
Finding well-defined clusters in data represents a fundamental challenge for many data-driven applications, and largely depends on good data representation.
Wavelet Networks: Scale-Translation Equivariant Learning From Raw Time-Series
In this work, we fill this gap by leveraging the symmetries inherent to time-series for the construction of equivariant neural network.
Attentive Group Equivariant Convolutional Networks
Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e. g., relative positions and poses).
Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Data
Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping.
Reinforcement Learning for Personalized Dialogue Management
Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e. g. take the personal context of users into account.
GP-HD: Using Genetic Programming to Generate Dynamical Systems Models for Health Care
The huge wealth of data in the health domain can be exploited to create models that predict development of health states over time.
Identifying Patient Groups based on Frequent Patterns of Patient Samples
In this paper we propose an approach that is able to find groups of patients based on a small sample of positive examples given by a domain expert.
A clustering-based reinforcement learning approach for tailored personalization of e-Health interventions
The time to learn intervention policies is limited as disengagement from the user can occur quickly.
