Search Results for author: Andrea Soltoggio

Found 12 papers, 7 papers with code

SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings

1 code implementation11 Dec 2021 Yuzhe Lu, Xinran Liu, Andrea Soltoggio, Soheil Kolouri

This paper focuses on non-parametric and data-independent learning from set-structured data using approximate nearest neighbor (ANN) solutions, particularly locality-sensitive hashing.

Context Meta-Reinforcement Learning via Neuromodulation

1 code implementation30 Oct 2021 Eseoghene Ben-Iwhiwhu, Jeffery Dick, Nicholas A. Ketz, Praveen K. Pilly, Andrea Soltoggio

Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments.

Continuous Control Meta Reinforcement Learning +1

Fast and automated biomarker detection in breath samples with machine learning

no code implementations24 May 2020 Angelika Skarysz, Dahlia Salman, Michael Eddleston, Martin Sykora, Eugenie Hunsicker, William H. Nailon, Kareen Darnley, Duncan B McLaren, C L Paul Thomas, Andrea Soltoggio

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.

Sliced Cramer Synaptic Consolidation for Preserving Deeply Learned Representations

no code implementations ICLR 2020 Soheil Kolouri, Nicholas A. Ketz, Andrea Soltoggio, Praveen K. Pilly

Deep neural networks suffer from the inability to preserve the learned data representation (i. e., catastrophic forgetting) in domains where the input data distribution is non-stationary, and it changes during training.

Incremental Learning

Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems

1 code implementation27 Apr 2020 Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick, Wen-Hua Chen, Praveen Pilly, Andrea Soltoggio

Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning.

Meta Reinforcement Learning online learning +1

Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture

1 code implementation21 Sep 2019 Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Jeffery Dick, Yang Hu, Nicholas Ketz, Soheil Kolouri, Jeffrey L. Krichmar, Praveen Pilly, Andrea Soltoggio

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).

Decision Making reinforcement-learning

A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs

no code implementations19 Jul 2019 Ling Jiang, Yang Hu, Xilin Xia, Qiuhua Liang, Andrea Soltoggio

Few attempts have been made for urban topography which is typically an integration of complex man-made and natural features.

A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation

1 code implementation6 Jul 2018 Yang Hu, Andrea Soltoggio, Russell Lock, Steve Carter

The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resolution.

Semantic Segmentation

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks

no code implementations30 Mar 2017 Andrea Soltoggio, Kenneth O. Stanley, Sebastian Risi

Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) use simulated evolution in-silico to breed plastic neural networks with a large variety of dynamics, architectures, and plasticity rules: these artificial systems are composed of inputs, outputs, and plastic components that change in response to experiences in an environment.

Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification

no code implementations21 Feb 2017 Yanis Bahroun, Andrea Soltoggio

Recently, a new class of Hebbian-like and local unsupervised learning rules for neural networks have been developed that minimise a similarity matching cost-function.

General Classification Image Classification +2

Short-term plasticity as cause-effect hypothesis testing in distal reward learning

1 code implementation4 Feb 2014 Andrea Soltoggio

Asynchrony, overlaps and delays in sensory-motor signals introduce ambiguity as to which stimuli, actions, and rewards are causally related.

Two-sample testing

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