Fundamentals of Robotics: Linking Perception to Action (Series in Machine Perception and Artificial Intelligence)

2004 ◽  
Vol 57 (5) ◽  
pp. B27-B27
Author(s):  
Ming Xie, ◽  
RL Huston,
Keyword(s):  
Artificial Intelligence ◽  
Machine Perception

scholarly journals Movement, activity and action: the role of knowledge in the perception of motion

1997 ◽  
Vol 352 (1358) ◽  
pp. 1257-1265 ◽  
Author(s):  
Aaron F. Bobick
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Recent Work ◽  
Motion Perception ◽  
Action Understanding ◽  
Movement Activity ◽  
Machine Perception ◽  
Geometric Techniques ◽  
Gesture Understanding

This paper presents several approaches to the machine perception of motion and discusses the role and levels of knowledge in each. In particular, different techniques of motion understanding as focusing on one of movement, activity or action are described. Movements are the most atomic primitives, requiring no contextual or sequence knowledge to be recognized; movement is often addressed using either view–invariant or view–specific geometric techniques. Activity refers to sequences of movements or states, where the only real knowledge required is the statistics of the sequence; much of the recent work in gesture understanding falls within this category of motion perception. Finally, actions are larger–scale events, which typically include interaction with the environment and causal relationships; action understanding straddles the grey division between perception and cognition, computer vision and artificial intelligence. These levels are illustrated with examples drawn mostly from the group's work in understanding motion in video imagery. It is argued that the utility of such a division is that it makes explicit the representational competencies and manipulations necessary for perception.

scholarly journals The potential of artificial intelligence in enhancing adult weight loss: A scoping review

2021 ◽  
pp. 1-59
Author(s):  
Han Shi Jocelyn CHEW ◽  
Wei How Darryl ANG ◽  
Ying LAU
Keyword(s):  
Artificial Intelligence ◽  
Weight Loss ◽  
Scoping Review ◽  
Prediction Models ◽  
Predictive Analytics ◽  
Self Regulation ◽  
Self Control ◽  
Average Weight ◽  
Machine Perception ◽  
Management Interventions

Abstract Objective: To present an overview of how artificial intelligence (AI) could be used to regulate eating and dietary behaviours, exercise behaviours and weight loss. Design: A scoping review of global literature published from inception to 15 December 2020 was conducted according to Arksey and O’Malley’s five-step framework. Eight databases (CINAHL, Cochrane–Central, Embase, IEEE Xplore, PsycINFO, PubMed, Scopus and Web of Science) were searched. Included studies were independently screened for eligibility by two reviewers with good interrater reliability (k= 0.96). Results: 66 out of 5573 potential studies were included, representing more than 2,031 participants. Three tenets of self-regulation were identified - self-monitoring (n=66, 100%), optimization of goal-setting (n=10, 15.2%) and self-control (n= 10, 15.2%). Articles were also categorised into three AI applications namely machine perception (n=50), predictive analytics only (n=6), and real-time analytics with personalised micro-interventions (n=10). Machine perception focused on recognizing food items, eating behaviours, physical activities and estimating energy balance. Predictive analytics focused on predicting weight loss, intervention adherence, dietary lapses and emotional eating. Studies on the last theme focused on evaluating AI-assisted weight management interventions that instantaneously collected behavioural data, optimised prediction models for behavioural lapse events and enhance behavioural self-control through adaptive and personalized nudges/prompts. Only six studies reported average weight losses (2.4% to 4.7%) of which two were statistically significant. Conclusion: The use of AI for weight loss is still undeveloped. Based on this study findings, we proposed a framework on the applicability of AI for weight loss but cautioned its contingency upon engagement and contextualisation.

scholarly journals Detecting Spurious Correlations With Sanity Tests for Artificial Intelligence Guided Radiology Systems

2021 ◽  
Vol 3 ◽  
Author(s):  
Usman Mahmood ◽  
Robik Shrestha ◽  
David D. B. Bates ◽  
Lorenzo Mannelli ◽  
Giuseppe Corrias ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Best Practices ◽  
Learning System ◽  
Clinical Validation ◽  
Efficacy And Safety ◽  
Analytical Validation ◽  
Validation Data ◽  
Machine Perception ◽  
Computed Tomography Scans ◽  
Development Data

Artificial intelligence (AI) has been successful at solving numerous problems in machine perception. In radiology, AI systems are rapidly evolving and show progress in guiding treatment decisions, diagnosing, localizing disease on medical images, and improving radiologists' efficiency. A critical component to deploying AI in radiology is to gain confidence in a developed system's efficacy and safety. The current gold standard approach is to conduct an analytical validation of performance on a generalization dataset from one or more institutions, followed by a clinical validation study of the system's efficacy during deployment. Clinical validation studies are time-consuming, and best practices dictate limited re-use of analytical validation data, so it is ideal to know ahead of time if a system is likely to fail analytical or clinical validation. In this paper, we describe a series of sanity tests to identify when a system performs well on development data for the wrong reasons. We illustrate the sanity tests' value by designing a deep learning system to classify pancreatic cancer seen in computed tomography scans.

scholarly journals Symmetry, Combinatorics, Artificial Intelligence, Music and Spectroscopy

Symmetry ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1850
Author(s):  
Krishnan Balasubramanian
Keyword(s):  
Artificial Intelligence ◽  
Music Theory ◽  
Esr Spectra ◽  
Machine Construction ◽  
Multiple Quantum ◽  
Magic Squares ◽  
Machine Perception ◽  
Musical Patterns ◽  
Spectroscopic Signatures ◽  
Musical Chords

Symmetry forms the foundation of combinatorial theories and algorithms of enumeration such as Möbius inversion, Euler totient functions, and the celebrated Pólya’s theory of enumeration under the symmetric group action. As machine learning and artificial intelligence techniques play increasingly important roles in the machine perception of music to image processing that are central to many disciplines, combinatorics, graph theory, and symmetry act as powerful bridges to the developments of algorithms for such varied applications. In this review, we bring together the confluence of music theory and spectroscopy as two primary disciplines to outline several interconnections of combinatorial and symmetry techniques in the development of algorithms for machine generation of musical patterns of the east and west and a variety of spectroscopic signatures of molecules. Combinatorial techniques in conjunction with group theory can be harnessed to generate the musical scales, intensity patterns in ESR spectra, multiple quantum NMR spectra, nuclear spin statistics of both fermions and bosons, colorings of hyperplanes of hypercubes, enumeration of chiral isomers, and vibrational modes of complex systems including supergiant fullerenes, as exemplified by our work on the golden fullerene C150,000. Combinatorial techniques are shown to yield algorithms for the enumeration and construction of musical chords and scales called ragas in music theory, as we exemplify by the machine construction of ragas and machine perception of musical patterns. We also outline the applications of Hadamard matrices and magic squares in the development of algorithms for the generation of balanced-pitch chords. Machine perception of musical, spectroscopic, and symmetry patterns are considered.

Developing and Delivering a High School Artificial Intelligence Course in Blended and Online Learning Environments

2020 ◽  
pp. 255-261
Author(s):  
Antonios Karampelas
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
High School ◽  
High School Students ◽  
Learning Environments ◽  
Community Schools ◽  
School Students ◽  
Online Learning Environments ◽  
Online Delivery ◽  
Machine Perception

The paper outlines the development and delivery of Artificial Intelligence to high school students of the American Community Schools of Athens, either as an independent course, or as part of a S.T.E.A.M. course, and the respective instructional design. The topics developed – Impact of Artificial Intelligence, Machine Perception, and Machine Learning – are discussed, including relevant assessments. Additionally, the transition to the online delivery of Artificial Intelligence is presented, followed by reflective views on student learning and suggested future steps.

scholarly journals Research and development of artificial intelligence in China

2016 ◽  
Vol 3 (4) ◽  
pp. 538-541 ◽  
Author(s):  
Jane Qiu
Keyword(s):  
Artificial Intelligence ◽  
Neurological Diseases ◽  
Machine Perception ◽  
Learning Machines ◽  
Chinese Academy Of Sciences ◽  
The World ◽  
Peking University ◽  
Set Up ◽  
World Champion ◽  
Academy Of Sciences

Abstract This year saw several milestones in the development of artificial intelligence. In March, AlphaGo, a computer algorithm developed by Google's London-based company, DeepMind, beat the world champion Lee Sedol at Go, an ancient Chinese board game. In October, the same company unveiled in the journal Nature its latest technique that allows a machine to solve tasks that require logic and reasoning, such as finding its way around the London Underground using a map it has never seen before. Such progress in recent years has provided significant impetus to developing cutting-edge learning machines around the world, including China. In 2015, the Chinese Academy of Sciences (CAS) set up the Centre for Excellence in Brain Science and Intelligence Technology—a consortium of laboratories from more than 20 CAS institutes and universities. Early this year, China rolled out the China Brain Project, a fifteen-year programme that will focus on brain mapping, neurological diseases and brain-inspired artificial intelligence. In a forum chaired by National Science Review's Executive Associative Editor, Mu-ming Poo, who also leads the CAS centre for excellence and the China Brain Project, several researchers discussed China's latest initiatives and progress in artificial intelligence, where the future lies and what the main challenges are. Yunji Chen Institute of Computing Technology, Chinese Academy of Sciences, Beijing Tieniu Tan Institute of Automation, Deputy President of Chinese Academy of Sciences, Beijing Yi Zeng Institute of Automation, Chinese Academy of Sciences, Beijing Hongbin Zha Director of Key Lab of Machine Perception (MOE), Peking University, Beijing Mu-ming Poo (Chair) Director of Institute of Neuroscience, Chinese Academy of Sciences, Shanghai

Teaching and Explanation: Aligning Priors between Machines and Humans

2021 ◽  
pp. 171-196
Author(s):  
José Hernández-Orallo ◽  
Cèsar Ferri
Keyword(s):  
Artificial Intelligence ◽  
Human Perception ◽  
Human Learning ◽  
Machine Intelligence ◽  
Human Intelligence ◽  
Machine Perception ◽  
Explainable Artificial Intelligence ◽  
The Future ◽  
The Way

Machine intelligence differs signficantly from human intelligence. While human perception has similarities to the way machine perception works, human learning is mostly a directed process, guided by other people: parents, teachers, ... The area of machine teaching is becoming increasingly popular as a different paradigm for making machines learn. In this chapter, we start from recent results in machine teaching that show the relevance of prior alignment between humans and machines. From here, we focus on the scenario when a machine has to teach humans, a situation more and more common in the future. Specifically, we analyse how machine teaching relates to explainable artificial intelligence, and how simplicity priors play a role beyond intelligibility. We illustrate this with a general teaching protocol and a few examples in several representation languages: feature-value vectors and sequences. Some straightforward experiments with humans indicate when a strong simplicity prior is --and is not-- sufficient.

Sign in / Sign up

Export Citation Format

Share Document