SeqNAS: Neural Architecture Search for Event Sequence Classification
Neural Architecture Search (NAS) methods are widely used in various industries to obtain high quality taskspecific solutions with minimal human intervention. Event Sequences find widespread use in various industrial applications including churn prediction customer segmentation fraud detection and fault diagnosis among others. Such data consist of categorical and real-valued components with irregular timestamps. Despite the usefulness of NAS methods previous approaches only have been applied to other domains images texts or time series. Our work addresses this limitation by introducing a novel NAS algorithm SeqNAS specifically designed for event sequence classification. We develop a simple yet expressive search space that leverages commonly used building blocks for event sequence classification including multihead self attention convolutions and recurrent cells. To perform the search we adopt sequential Bayesian Optimization and utilize previously trained models as an ensemble of teachers to augment knowledge distillation. As a result of our work we demonstrate that our method surpasses state of the art NAS methods and popular architectures suitable for sequence classification and holds great potential for various industrial applications.
Code (1)
Tasks
Bayesian OptimizationClassificationFault DiagnosisFraud DetectionKnowledge DistillationNeural Architecture SearchTime SeriesSimilar Papers 제목 키워드 기반
ClaPIM: Scalable Sequence CLAssification using Processing-In-Memory
DNA sequence classification is a fundamental task in computational biology with vast implications for applications such as disease prevention and drug design. Therefore, fast high-quality sequence classifiers are signifi…
ClassificationDrug DesignFormal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach
Formally verifying audio classification systems is essential to ensure accurate signal classification across real-world applications like surveillance, automotive voice commands, and multimedia content management, preven…
Audio ClassificationClassificationManagementReal-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
Event-based cameras are novel, efficient sensors inspired by the human vision system, generating an asynchronous, pixel-wise stream of data. Learning from such data is generally performed through event integration into i…
input filteringAdversarial Continual Learning
Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-speci…
Continual Learningimage-classificationImage ClassificationTSkips: Efficiency Through Explicit Temporal Delay Connections in Spiking Neural Networks
Spiking Neural Networks (SNNs) with their bio-inspired Leaky Integrate-and-Fire (LIF) neurons inherently capture temporal information. This makes them well-suited for sequential tasks like processing event-based data fro…
Gesture RecognitionHand Gesture RecognitionHand-Gesture RecognitionNavigate+4