Search Results for author:
Found 18 papers, 11 papers with code
A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation
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.
Deep Reinforcement Learning with Modulated Hebbian plus Q Network Architecture
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).
Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems
Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning.
SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings
This paper focuses on non-parametric and data-independent learning from set-structured data using approximate nearest neighbor (ANN) solutions, particularly locality-sensitive hashing.
The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning
This paper introduces a set of formally defined and transparent problems for reinforcement learning algorithms with the following characteristics: (1) variable degrees of observability (non-Markov observations), (2) distal and sparse rewards, (3) variable and hierarchical reward structure, (4) multiple-task generation, (5) variable problem complexity.
Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks
The key idea is that the isolation of specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in robust and effective distributed lifelong learning.
Context Meta-Reinforcement Learning via Neuromodulation
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments.
Wasserstein Task Embedding for Measuring Task Similarities
Lastly, we leverage the 2-Wasserstein embedding framework to embed tasks into a vector space in which the Euclidean distance between the embedded points approximates the proposed 2-Wasserstein distance between tasks.
Lifelong Reinforcement Learning with Modulating Masks
The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.
Short-term plasticity as cause-effect hypothesis testing in distal reward learning
Asynchrony, overlaps and delays in sensory-motor signals introduce ambiguity as to which stimuli, actions, and rewards are causally related.
Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification
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.
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
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.
A Multi-Scale Mapping Approach Based on a Deep Learning CNN Model for Reconstructing High-Resolution Urban DEMs
Few attempts have been made for urban topography which is typically an integration of complex man-made and natural features.
Fast and automated biomarker detection in breath samples with machine learning
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
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.
Improving the Segmentation of Scanning Probe Microscope Images using Convolutional Neural Networks
A wide range of techniques can be considered for segmentation of images of nanostructured surfaces.
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
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 encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed.
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
These components collaboratively tackle the trade-offs in on-device DRL training, improving timing and algorithm performance while minimizing the risk of out-of-memory (OOM) errors.
