A5001452696- EEG and Brain-Computer Interfaces
- Domain Adaptation and Few-Shot Learning
- Neural Networks and Applications
- Obstructive Sleep Apnea Research
- Online Learning and Analytics
- Non-Invasive Vital Sign Monitoring
- Sleep and Wakefulness Research
- Anomaly Detection Techniques and Applications
- COVID-19 diagnosis using AI
- Zebrafish Biomedical Research Applications
- Machine Learning and Data Classification
- ECG Monitoring and Analysis
- Neural dynamics and brain function
- Spinal Cord Injury Research
- Robotic Locomotion and Control
- Intelligent Tutoring Systems and Adaptive Learning
University of Southern California
2021-2024
University of Birmingham
2015
A novel model of self-organization early spinal circuitry based on a biologically realistic plant, sensors, and neuronal plasticity in conjunction with empirical observations fetal development. Without explicit need for guiding genetic rules, connection matrices emerge that support functional the mature pattern Ia to motoneuron connectivity circuitry.
In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicated machinery then deployed mitigate the forgetting of old are learned. This inherently slow. We propose Shared Knowledge (SKILL) challenge, which deploys decentralized population each sequentially different tasks, with all operating independently in parallel. After learning their respective share consolidate...
Machine learning is a crucial tool for both academic and real-world applications. Classification problems are often used as the preferred showcase in this space, which has led to wide variety of datasets being collected utilized myriad Unfortunately, there very little standardization how these collected, processed, disseminated. As new paradigms like lifelong or meta-learning become more popular, demand merging tasks at-scale evaluation algorithms also increased. This paper provides...
Abstract Recent spinal cord literature abounds with descriptions of genetic preprogramming and the molecular control circuit formation. In this paper we explore to what extent formation based on learning rather than could explain some prominent aspects connectivity patterns observed in animals. To test developed an artificial organism a basic musculoskeletal system proprioceptive sensors, connected neural network. We adjusted initially randomized gains network according Hebbian plasticity...
Abstract Accurate classification of sleep stages is crucial in medicine and neuroscience research, providing valuable insights for diagnoses understanding brain states. The current gold standard this task polysomnography (PSG), an expensive cumbersome process involving numerous electrodes, often performed unfamiliar clinic professionally annotated. Although commercial devices like smartwatches track sleep, their performance compares poorly with PSG. To address this, we present a neural...