A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Unified framework for testing deep learning models with concept activation vectors.
This paper analyzes the variability of Concept Activation Vectors (CAVs).
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
Future Connected and Automated Vehicles (CAV), and more generally ITS, will form a highly interconnected system. Such a paradigm is referred to as the Internet of Vehicles (herein Internet of CAVs) and is a prerequisite to orchestrate traffic flows in cities. For optimal decision making and supervision, traffic centres…
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), whic…
Deep learning skin lesion classifier explained using CAVs.
Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services. Such a transformation---which will be fuelled by concomitant advances in technologies for machine learnin…
In this paper we propose a novel observer-based method to improve the safety and security of connected and automated vehicle (CAV) transportation. The proposed method combines model-based signal filtering and anomaly detection methods. Specifically, we use adaptive extended Kalman filter (AEKF) to smooth sensor reading…
Researchers apply concept-based explainability to EEG data.
This paper improves transportation efficiency by teaching automated vehicles to cooperate.
Collision avoidance is a critical task in many applications, such as ADAS (advanced driver-assistance systems), industrial automation and robotics. In an industrial automation setting, certain areas should be off limits to an automated vehicle for protection of people and high-valued assets. These areas can be quaranti…
Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.