Search Results for author: German I. Parisi

Found 18 papers, 3 papers with code

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

1 code implementation14 Sep 2020 Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.

Continual Learning

Online Continual Learning on Sequences

no code implementations20 Mar 2020 German I. Parisi, Vincenzo Lomonaco

Online continual learning (OCL) refers to the ability of a system to learn over time from a continuous stream of data without having to revisit previously encountered training samples.

Continual Learning Incremental Learning

Human Action Recognition and Assessment via Deep Neural Network Self-Organization

no code implementations4 Jan 2020 German I. Parisi

In this chapter, I introduce a set of hierarchical models for the learning and recognition of actions from depth maps and RGB images through the use of neural network self-organization.

Action Recognition Continual Learning

Rethinking Continual Learning for Autonomous Agents and Robots

no code implementations2 Jul 2019 German I. Parisi, Christopher Kanan

Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i. e., a condition in which new incoming information strongly interferes with previously learned representations.

Continual Learning Transfer Learning

A Personalized Affective Memory Neural Model for Improving Emotion Recognition

no code implementations23 Apr 2019 Pablo Barros, German I. Parisi, Stefan Wermter

Recent models of emotion recognition strongly rely on supervised deep learning solutions for the distinction of general emotion expressions.

Emotion Recognition

On the role of neurogenesis in overcoming catastrophic forgetting

no code implementations6 Nov 2018 German I. Parisi, Xu Ji, Stefan Wermter

Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated.

Incremental Learning

Assessing the Contribution of Semantic Congruency to Multisensory Integration and Conflict Resolution

no code implementations15 Oct 2018 Di Fu, Pablo Barros, German I. Parisi, Haiyan Wu, Sven Magg, Xun Liu, Stefan Wermter

The efficient integration of multisensory observations is a key property of the brain that yields the robust interaction with the environment.

Unsupervised Expectation Learning for Multisensory Binding

no code implementations27 Sep 2018 Pablo Barros, German I. Parisi, Manfred Eppe, Stefan Wermter

The model adapts concepts of expectation learning to enhance the unisensory representation based on the learned bindings.

Multi-modal Feedback for Affordance-driven Interactive Reinforcement Learning

no code implementations26 Jul 2018 Francisco Cruz, German I. Parisi, Stefan Wermter

Additionally, we modulate the influence of sensory-driven feedback in the IRL task using goal-oriented knowledge in terms of contextual affordances.


Towards Modeling the Interaction of Spatial-Associative Neural Network Representations for Multisensory Perception

no code implementations13 Jul 2018 German I. Parisi, Jonathan Tong, Pablo Barros, Brigitte Röder, Stefan Wermter

In the associative layer, congruent audiovisual representations are obtained via the experience-driven development of feature-based associations.

Causal Inference

Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization

1 code implementation28 May 2018 German I. Parisi, Jun Tani, Cornelius Weber, Stefan Wermter

Both growing networks can expand in response to novel sensory experience: the episodic memory learns fine-grained spatiotemporal representations of object instances in an unsupervised fashion while the semantic memory uses task-relevant signals to regulate structural plasticity levels and develop more compact representations from episodic experience.

Active Learning Continuous Object Recognition +1

Continual Lifelong Learning with Neural Networks: A Review

no code implementations21 Feb 2018 German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, Stefan Wermter

Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan.

Retrieval Transfer Learning

Closing the loop on multisensory interactions: A neural architecture for multisensory causal inference and recalibration

no code implementations19 Feb 2018 Jonathan Tong, German I. Parisi, Stefan Wermter, Brigitte Röder

Furthermore, we propose that these unisensory and multisensory neurons play dual roles in i) encoding spatial location as separate or integrated estimates and ii) accumulating evidence for the independence or relatedness of multisensory stimuli.

Causal Inference

An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction

no code implementations22 Dec 2017 Luiza Mici, German I. Parisi, Stefan Wermter

During visuomotor tasks, robots must compensate for temporal delays inherent in their sensorimotor processing systems.

A self-organizing neural network architecture for learning human-object interactions

no code implementations5 Oct 2017 Luiza Mici, German I. Parisi, Stefan Wermter

We show that our unsupervised model shows competitive classification results on the benchmark dataset with respect to strictly supervised approaches.

Human-Object Interaction Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.