124 citations · 190 across the 20 of their papers we have counts for
21 papers
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
Saptarshi Nath, Inish M. D'Souza, Antonio Carta +2
In lifelong reinforcement learning, retaining previously learned policies is not sufficient for effective transfer to a new task. Useful knowledge may be distributed across several…
Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems
Saptarshi Nath, Christos Peridis, Eseoghene Benjamin +7
Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facin…
Synaptic Modulation using Interspike Intervals Increases Energy Efficiency of Spiking Neural Networks
Dylan Adams, Magda Zajaczkowska, Ashiq Anjum +2
Despite basic differences between Spiking Neural Networks (SNN) and Artificial Neural Networks (ANN), most research on SNNs involve adapting ANN-based methods for SNNs. Pruning (dr…
Statistical Context Detection for Deep Lifelong Reinforcement Learning
Jeffery Dick, Saptarshi Nath, Christos Peridis +3
Context detection involves labeling segments of an online stream of data as belonging to different tasks. Task labels are used in lifelong learning algorithms to perform consolidat…
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
Zexin Li, Aritra Samanta, Yufei Li +3
Autonomous robotic systems, like autonomous vehicles and robotic search and rescue, require efficient on-device training for continuous adaptation of Deep Reinforcement Learning (D…
Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks
Saptarshi Nath, Christos Peridis, Eseoghene Ben-Iwhiwhu +5
Lifelong learning agents aim to learn multiple tasks sequentially over a lifetime. This involves the ability to exploit previous knowledge when learning new tasks and to avoid forg…
The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning
Andrea Soltoggio, Eseoghene Ben-Iwhiwhu, Christos Peridis +4
This paper introduces a set of formally defined and transparent problems for reinforcement learning algorithms with the following characteristics: (1) variable degrees of observabi…
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Megan M. Baker, Alexander New, Mario Aguilar-Simon +44
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks enc…
Lifelong Reinforcement Learning with Modulating Masks
Eseoghene Ben-Iwhiwhu, Saptarshi Nath, Praveen K. Pilly +2
Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, includin…
Wasserstein Task Embedding for Measuring Task Similarities
Xinran Liu, Yikun Bai, Yuzhe Lu +2
Measuring similarities between different tasks is critical in a broad spectrum of machine learning problems, including transfer, multi-task, continual, and meta-learning. Most curr…
SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings
Yuzhe Lu, Xinran Liu, Andrea Soltoggio +1
Learning from set-structured data is an essential problem with many applications in machine learning and computer vision. This paper focuses on non-parametric and data-independent…
Context Meta-Reinforcement Learning via Neuromodulation
Eseoghene Ben-Iwhiwhu, Jeffery Dick, Nicholas A. Ketz +2
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic represent…
Improving the Segmentation of Scanning Probe Microscope Images using Convolutional Neural Networks
Steff Farley, Jo E. A. Hodgkinson, Oliver M. Gordon +4
A wide range of techniques can be considered for segmentation of images of nanostructured surfaces. Manually segmenting these images is time-consuming and results in a user-depende…
Fast and automated biomarker detection in breath samples with machine learning
Angelika Skarysz, Dahlia Salman, Michael Eddleston +7
Volatile organic compounds (VOCs) in human breath can reveal a large spectrum of health conditions and can be used for fast, accurate and non-invasive diagnostics. Gas chromatograp…
Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems
Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick +3
Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) al…
Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture
Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Jeffery Dick +6
This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA). The hy…
A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs
Ling Jiang, Yang Hu, Xilin Xia +2
The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effectiv…
A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation
Yang Hu, Andrea Soltoggio, Russell Lock +1
In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-s…
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
Andrea Soltoggio, Kenneth O. Stanley, Sebastian Risi
Biological plastic neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifetime learning. The interplay of these elements…
Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification
Yanis Bahroun, Andrea Soltoggio
Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different data sets using the same underlying rules thanks to the autonomous disc…
Short-term plasticity as cause-effect hypothesis testing in distal reward learning
Andrea Soltoggio
Asynchrony, overlaps and delays in sensory-motor signals introduce ambiguity as to which stimuli, actions, and rewards are causally related. Only the repetition of reward episodes…