Research

This section details my scientific publications, primarily focused on advancing machine learning and deep neural networks. My involvement has spanned, from conceptualizing the ideas and developing machine learning models, to providing support to my colleagues.

Featured Publications

MAS Emergence Safety

MAS Emergence Safety

ISoLA 2024•2024-10-27

Formalized MAS emergence misalignment; proposed safety mitigation strategies.

Voronoi Data Augmentation

Voronoi Data Augmentation

ICAART 2023•2023-02-24

VoronoiPatches improves CNN robustness via non-linear recombination augmentation.

RNN Memory Limits

RNN Memory Limits

ICAART 2022•2022-02-25

Investigated memory limits of RNNs in recalling uncorrelated sequences.

Audio Vision Transformer

Audio Vision Transformer

Interspeech 2021•2021-03-05

Vision Transformer on spectrograms for audio classification, with data augmentation.

Other

Filter by Topic:

complex-systems (6)audio-classification (7)deep-learning (12)machine-learning (9)artificial-life (5)neural-networks (5)self-organization (5)computer-vision (5)anomaly-detection (5)

Aquarium MARL Environment

Aquarium MARL Environment

ICAART 2024•2024-01-13

Aquarium: Open-source MARL environment for predator-prey studies.

Primate Subsegment Sorting

Primate Subsegment Sorting

ICAART 2023•2023-06-25

Binary subsegment presorting improves noisy primate sound classification.

Emergent Social Dynamics

Emergent Social Dynamics

ALIFE 2023•2023-05-01

Artificial chemistry networks develop predictive models via surprise minimization.

Autoencoder Trajectory Compression

Autoencoder Trajectory Compression

ICAART 2023•2023-02-25

LSTM autoencoder better DP for trajectory compression (Fréchet/DTW).

Organism Network Emergence

Organism Network Emergence

SSCI 2022•2022-12-01

Self-replicating networks collaborate forming higher-level Organism Networks with emergent functionalities.

Extended Self-Replication

Extended Self-Replication

Artificial Life 28 (2022)•2022-08-01

Journal extension: self-replication, noise robustness, emergence, dynamical system analysis.

RL Anomaly Detection

RL Anomaly Detection

AAMAS 22•2022-05-09

Perspective on anomaly detection challenges and future in reinforcement learning.

Tasked Self-Replication

Tasked Self-Replication

ALIFE 2021•2021-03-06

Self-replicating networks perform tasks, exploring stabilization in artificial chemistry.

Primate Vocalization Classification

Primate Vocalization Classification

Interspeech 2021•2021-03-04

Deep BiLSTM classifies primate vocalizations for acoustic wildlife monitoring.

Acoustic Leak Detection

Acoustic Leak Detection

ICAART 2021•2021-03-03

Anomaly detection models for acoustic leak detection in water networks.

Sound Anomaly Transfer

Sound Anomaly Transfer

ICAART 2021•2021-03-02

Image nets detect acoustic anomalies in machinery via spectrograms.

Anomalous Sound Features

Anomalous Sound Features

IJCNN 2021•2021-03-01

Pretrained networks extract features for anomalous industrial sound detection.

Surgical-Mask Detection

Surgical-Mask Detection

Interspeech 2020•2020-10-25

CNN mask detection in speech using augmented spectrograms.

AV Meantime Coverage

AV Meantime Coverage

AGILE-GISS 2020•2020-07-15

Analyzing service coverage of parked AVs during downtime ('meantime').

PEOC OOD Detection

PEOC OOD Detection

ICANN 2020•2020-06-01

PEOC uses policy entropy for OOD detection in deep RL.

3D Primitive Segmentation

3D Primitive Segmentation

VISIGRAPP 2020•2020-05-01

Hybrid method segments/fits primitives in large 3D point clouds.

Soccer Team Vectors

Soccer Team Vectors

ECML PKDD 2019•2020-03-01

STEVE learns soccer team embeddings from match data for analysis.

Deep Audio Baselines

Deep Audio Baselines

Interspeech 2019•2019-07-05

Deep learning audio baseline for Interspeech 2019 ComParE challenge.

Neural Self-Replication

Neural Self-Replication

ALIFE 2019•2019-07-01

Neural networks replicating weights, inspired by biology and artificial life.

Learned Trajectory Annotation

Learned Trajectory Annotation

26th ACM SIGSPATIAL•2018-11-01

Unsupervised autoencoder learns spatial context from trajectory data for annotation.