AIMC Topic: Learning

Clear Filters Showing 251 to 260 of 1397 articles

Phar-LSTM: a pharmacological representation-based LSTM network for drug-drug interaction extraction.

PeerJ
Pharmacological drug interactions are among the most common causes of medication errors. Many different methods have been proposed to extract drug-drug interactions from the literature to reduce medication errors over the last few years. However, the...

Human motor augmentation with an extra robotic arm without functional interference.

Science robotics
Extra robotic arms (XRAs) are gaining interest in neuroscience and robotics, offering potential tools for daily activities. However, this compelling opportunity poses new challenges for sensorimotor control strategies and human-machine interfaces (HM...

Artificial Intelligence Agents for Materials Sciences.

Journal of chemical information and modeling
The artificial intelligence (AI) tools based on large-language models may serve as a demonstration that we are reaching a groundbreaking new paradigm in which machines themselves will generate knowledge autonomously. This statement is based on the as...

Beyond multilayer perceptrons: Investigating complex topologies in neural networks.

Neural networks : the official journal of the International Neural Network Society
This study delves into the crucial aspect of network topology in artificial neural networks (NNs) and its impact on model performance. Addressing the need to comprehend how network structures influence learning capabilities, the research contrasts tr...

Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach.

Neural networks : the official journal of the International Neural Network Society
The 6-Degree-of-Freedom (6-DoF) robotic grasping is a fundamental task in robot manipulation, aimed at detecting graspable points and corresponding parameters in a 3D space, i.e affordance learning, and then a robot executes grasp actions with the de...

Implications of capacity-limited, generative models for human vision.

The Behavioral and brain sciences
Although discriminative deep neural networks are currently dominant in cognitive modeling, we suggest that capacity-limited, generative models are a promising avenue for future work. Generative models tend to learn both local and global features of s...

Where do the hypotheses come from? Data-driven learning in science and the brain.

The Behavioral and brain sciences
Everyone agrees that testing hypotheses is important, but Bowers et al. provide scant details about where hypotheses about perception and brain function should come from. We suggest that the answer lies in considering how information about the outsid...

Perceptual learning in humans: An active, top-down-guided process.

The Behavioral and brain sciences
Deep neural network (DNN) models of human-like vision are typically built by feeding blank slate DNN visual images as training data. However, the literature on human perception and perceptual learning suggests that developing DNNs that truly model hu...

Fear-Neuro-Inspired Reinforcement Learning for Safe Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence
Ensuring safety and achieving human-level driving performance remain challenges for autonomous vehicles, especially in safety-critical situations. As a key component of artificial intelligence, reinforcement learning is promising and has shown great ...

Black-box attacks on dynamic graphs via adversarial topology perturbations.

Neural networks : the official journal of the International Neural Network Society
Research and analysis of attacks on dynamic graph is beneficial for information systems to investigate vulnerabilities and strength abilities in resisting malicious attacks. Existing attacks on dynamic graphs mainly focus on rewiring original graph s...