Search

In a recent paper, Flament et al (1999) studied the learning to flex the elbow fast. They concluded from their data that time-related parameters (e.g. movement time) changed faster during learning than magnitude-related parameters (e.g. peak velocity), and discussed this finding in terms of neural substrates responsible for the apparently different learning mechanisms. In this note, I will argue that finding different time constants does not imply different learning mechanisms. I will give a theoretical example of the development of parameters during learning to move faster. Despite the fact that I model only one learning process, various kinematic parameters show different time courses of learning. The differences the model predicts are comparable with the experimental results.

Reaching out for an object is often described as consisting of two components that are based on different visual information. Information about the object’s position and orientation guides the hand to the object, while information about the object’s shape and size determines how the fingers move relative to the thumb to grasp it. We propose an alternative description, which consists of determining suitable positions on the object — on the basis of its shape, surface roughness, and so on — and then moving one’s thumb and fingers more or less independently to these positions. We modelled this description using a minimum jerk approach, whereby the finger and thumb approach their respective target positions approximately orthogonally to the surface. Our model predicts how experimental variables such as object size, movement speed, fragility, and required accuracy will influence the timing and size of the maximum aperture of the hand. An extensive review of experimental studies on grasping showed that the predicted influences correspond to human behaviour.

Graph Anomaly Detection (GAD) is a technique used to identify abnormal nodes within graphs, finding applications in network security, fraud detection, social media spam detection, and various other domains. A common method for GAD is Graph Auto-Encoders (GAEs), which encode graph data into node representations and identify anomalies by assessing the reconstruction quality of the graphs based on these representations. However, existing GAE models are primarily optimized for direct link reconstruction, resulting in nodes connected in the graph being clustered in the latent space. As a result, they excel at detecting cluster-type structural anomalies but struggle with more complex structural anomalies that do not conform to clusters. To address this limitation, we propose a novel solution called GAD-NR, a new variant of GAE that incorporates neighborhood reconstruction for graph anomaly detection. GAD-NR aims to reconstruct the entire neighborhood of a node, encompassing the local structure, self-attributes, and neighbor attributes, based on the corresponding node representation. By comparing the neighborhood reconstruction loss between anomalous nodes and normal nodes, GAD-NR can effectively detect any anomalies. Extensive experimentation conducted on six real-world datasets validates the effectiveness of GAD-NR, showcasing significant improvements (by up to 30% in AUC) over state-of-the-art competitors. The source code for GAD-NR is openly available. Importantly, the comparative analysis reveals that the existing methods perform well only in detecting one or two types of anomalies out of the three types studied. In contrast, GAD-NR excels at detecting all three types of anomalies across the datasets, demonstrating its comprehensive anomaly detection capabilities., Comment: Accepted at the 17th ACM International Conference on Web Search and Data Mining (WSDM-2024)