Embodying Cognition

2012 ◽  
pp. 1798-1818 ◽  
Author(s):  
David Casacuberta ◽  
Saray Ayala ◽  
Jordi Vallverdú
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
The Real ◽  
Specific Reading ◽  
Natural Forms ◽  
Lego Mindstorms ◽  
The Mind ◽  
Embodied Agent ◽  
Reasonable Model

After several decades of success in different areas and numerous effective applications, algorithmic Artificial Intelligence has revealed its limitations. If in our quest for artificial intelligence we want to understand natural forms of intelligence, we need to shift/move from platform-free algorithms to embodied and embedded agents. Under the embodied perspective, intelligence is not so much a matter of algorithms, but of the continuous interactions of an embodied agent with the real world. In this paper we adhere to a specific reading of the embodied view usually known as enactivism, to argue that 1) It is a more reasonable model of how the mind really works; 2) It has both theoretical and empirical benefits for Artificial Intelligence and 3) Can be easily implemented in simple robotic sets like Lego Mindstorms (TM). In particular, we will explore the computational role that morphology can play in artificial systems. We will illustrate our ideas presenting several Lego Mindstorms robots where morphology is critical for the robot’s behaviour.

Embodying Cognition

2010 ◽  
pp. 344-366 ◽  
Author(s):  
David Casacuberta ◽  
Saray Ayala ◽  
Jordi Vallverdú
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
The Real ◽  
Specific Reading ◽  
Natural Forms ◽  
Lego Mindstorms ◽  
The Mind ◽  
Embodied Agent ◽  
Reasonable Model

After several decades of success in different areas and numerous effective applications, algorithmic Artificial Intelligence has revealed its limitations. If in our quest for artificial intelligence we want to understand natural forms of intelligence, we need to shift/move from platform-free algorithms to embodied and embedded agents. Under the embodied perspective, intelligence is not so much a matter of algorithms, but of the continuous interactions of an embodied agent with the real world. In this paper we adhere to a specific reading of the embodied view usually known as enactivism, to argue that 1) It is a more reasonable model of how the mind really works; 2) It has both theoretical and empirical benefits for Artificial Intelligence and 3) Can be easily implemented in simple robotic sets like Lego Mindstorms (TM). In particular, we will explore the computational role that morphology can play in artificial systems. We will illustrate our ideas presenting several Lego Mindstorms robots where morphology is critical for the robot’s behaviour.

scholarly journals How to train your robot with deep reinforcement learning: lessons we have learned

2021 ◽  
pp. 027836492098785
Author(s):  
Julian Ibarz ◽  
Jie Tan ◽  
Chelsea Finn ◽  
Mrinal Kalakrishnan ◽  
Peter Pastor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Case Studies ◽  
Real World ◽  
Review Article ◽  
The Real ◽  
Complex Skills ◽  
Real World Learning ◽  
Level Sensor ◽  
Embodied Agent

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low-level sensor observations. Although a large portion of deep RL research has focused on applications in video games and simulated control, which does not connect with the constraints of learning in real environments, deep RL has also demonstrated promise in enabling physical robots to learn complex skills in the real world. At the same time, real-world robotics provides an appealing domain for evaluating such algorithms, as it connects directly to how humans learn: as an embodied agent in the real world. Learning to perceive and move in the real world presents numerous challenges, some of which are easier to address than others, and some of which are often not considered in RL research that focuses only on simulated domains. In this review article, we present a number of case studies involving robotic deep RL. Building off of these case studies, we discuss commonly perceived challenges in deep RL and how they have been addressed in these works. We also provide an overview of other outstanding challenges, many of which are unique to the real-world robotics setting and are not often the focus of mainstream RL research. Our goal is to provide a resource both for roboticists and machine learning researchers who are interested in furthering the progress of deep RL in the real world.

scholarly journals City brain: practice of large‐scale artificial intelligence in the real world

2019 ◽  
Vol 1 (1) ◽  
pp. 28-37 ◽  
Author(s):  
Jianfeng Zhang ◽  
Xian‐Sheng Hua ◽  
Jianqiang Huang ◽  
Xu Shen ◽  
Jingyuan Chen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Large Scale ◽  
The Real

Artificial Intelligence Screening for Diabetic Retinopathy: the Real-World Emerging Application

2019 ◽  
Vol 19 (9) ◽  
Author(s):  
Valentina Bellemo ◽  
Gilbert Lim ◽  
Tyler Hyungtaek Rim ◽  
Gavin S. W. Tan ◽  
Carol Y. Cheung ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Diabetic Retinopathy ◽  
Real World ◽  
The Real

Special Issue on Integrated Knowledge on Innovative Robot Mechanisms

2018 ◽  
Vol 30 (6) ◽  
pp. 845-845
Author(s):  
Naoyuki Takesue ◽  
Koichi Koganezawa ◽  
Kenjiro Tadakuma
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Computer Control ◽  
Computer Processing ◽  
Knowledge System ◽  
Mechanical Work ◽  
The Other ◽  
Special Issue ◽  
The Real ◽  
Integrated Knowledge

A robot is a system integrated with many elements such as actuators, sensors, computers, and mechanical components. Currently, progress in the field of artificial intelligence induced by tremendous improvements in computer processing capabilities has enabled robots to behave in a more sophisticated manner, which is drawing considerable attention. On the other hand, the mechanism that directly produces robot movements and mechanical work sometimes brings out some competencies that cannot be provided solely by computer control that relies on sensor feedback. This special issue on “Integrated Knowledge on Innovative Robot Mechanisms” aims to introduce a knowledge system for robot mechanisms that bring forth useful and innovative functions and values. The editors hope that the studies discussed in this special issue will help in the realization and further improvement of the mechanical functions of robots in the real world.

New breakthroughs or dead-ends?

1994 ◽  
Vol 349 (1689) ◽  
pp. 1-13 ◽  
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Physical System ◽  
Royal Society ◽  
Existence Proof ◽  
Frame Problem ◽  
Psychological Theories ◽  
New Concepts ◽  
Human Thinking ◽  
The Mind

Artificial intelligence (AI), at its inception, offered new concepts for formulating psychological theories and a new methodology for testing them. It also promised an ‘existence proof’ that intelligence could be implemented in a physical system. These promises are still controversial, both in AI and in philosophy. Some researchers favour connectionism, a form of AI that has blossomed relatively recently. Others believe ‘classical’ AI insights are needed to model many types of human thinking. Some eschew classical AI (and the associated frame problem) in favour of robots ‘embedded’ in the real world. Similarly, some reject functionalist interpretations of AI, arguing that intentionality cannot be grounded in syntactic and/or simulated and/or non-evolved systems. Consciousness is highly problematic: many doubt that any computational (or even scientific) account could explain it. The papers presented at this Royal Society/British Academy meeting explore these issues. Even without dead-ends, the routes taken in AI accounts of the mind may lead in unexpected directions.

scholarly journals Adversarial Examples in Physical World

2021 ◽  
Author(s):  
Jiakai Wang
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Potential Risk ◽  
Real World ◽  
Deep Neural Networks ◽  
Physical World ◽  
The Real ◽  
Wide Range ◽  
Adversarial Examples ◽  
Ai Safety

Although deep neural networks (DNNs) have already made fairly high achievements and a very wide range of impact, their vulnerability attracts lots of interest of researchers towards related studies about artificial intelligence (AI) safety and robustness this year. A series of works reveals that the current DNNs are always misled by elaborately designed adversarial examples. And unfortunately, this peculiarity also affects real-world AI applications and places them at potential risk. we are more interested in physical attacks due to their implementability in the real world. The study of physical attacks can effectively promote the application of AI techniques, which is of great significance to the security development of AI.

‘We are both father and mother together in this generation’: Physical and Intellectual Creations in ‘Of the Affection of Fathers to Their Children’ and King Lear

2020 ◽  
pp. 109-128
Author(s):  
Peter G. Platt
Keyword(s):  
Real World ◽  
King Lear ◽  
Missed Opportunities ◽  
The Real ◽  
Parents And Children ◽  
The Mind

This chapter examines the connection between physical and intellectual creations in “Of the Affection of Fathers to Their Children” (2.8) and King Lear. It argues that Montaigne is at once more optimistic and more pessimistic about the love between parents and children than Shakespeare in Lear: he both argues for the natural bond between parents and their offspring and anatomizes the treacheries and missed opportunities for achieving this bond that happen in the real world, beyond ideals. Further, the even greater connection between essay and play is the shared fascination with non-bodily creations. For Montaigne, “Of the Affection” ultimately argues that “what we engender by the mind, the fruits of our courage, sufficiency, or spirit, are brought forth by a far more noble part than the corporeal and more our own.” For Shakespeare, King Lear provides a sustained meditation not only on filial impiety but on the mind’s engenderings: those of “fools and madmen” (3.4.75), “noble philosopher[s]” (3.4.160), and the theater itself.

Is The Mind-Body Problem Empirical?

1987 ◽  
Vol 17 (3) ◽  
pp. 505-532 ◽  
Author(s):  
Jeffrey Foss
Keyword(s):  
Empirical Evidence ◽  
Real World ◽  
Conceptual Analysis ◽  
Body Problem ◽  
A Priori ◽  
The Real ◽  
Existential Import ◽  
Mind Body Problem ◽  
The Mind

There is no problem more paradigmatically philosophical than the mind-body problem. Nevertheless, I will argue that the problem is empirical. I am not even suggesting that conceptual analysis of the various mind-body theories be abandoned – just as I could not suggest it be abandoned for theories in physics or biology. But unlike the question, ‘Is every even number greater than 2 equal to the sum of two primes?’ the mind-body problem cannot be solved a priori, by analysis alone; though I will not argue this thesis here, it is nearly obvious, since purported solutions must make matter of fact claims, heavy with existential import, about the real world. By contrast, an investigation of the sensitivity of the mind-body problem to empirical evidence will show that purported solutions to the problem are empirically testable, to a degree consistent with philosophy giving a clarified mind-body problem to the sciences. I offer the bold outlines of such an investigation here.

scholarly journals Mózg jako nowy wszechświat – wokół Incepcji Christophera Nolana

2021 ◽  
Vol 28 (37) ◽  
pp. 207-220
Author(s):  
Marcin Kowalczyk
Keyword(s):  
Human Brain ◽  
Science Fiction ◽  
Real World ◽  
Paradigm Shift ◽  
Space Travel ◽  
The Real ◽  
Main Thesis ◽  
Christopher Nolan ◽  
The Mind ◽  
The Brain

The article shows the growing interest of science fiction cinema in the human brain and related concepts, such as mind or consciousness. Nowadays, when distant space travel seems unreachable, artists find the exploration potential of the brain very promising. Thus, the main thesis of this analysis says that the brain has become for science fiction cinema the new universe. An excellent example of this paradigm shift is Inception (dir. Christopher Nolan, 2010). In the movie, the mind is depicted as a physical and accessible place, where we can find a lot of mysteries to solve. The characters travel to the deepest parts of subconsciousness because the processes inside the brain are the key to understanding and changing the real world. The article also shows how the director uses the achievements of science fiction cinema and, at the same time, that he postulates a new way of considering the issues relevant to modern neuroscience.

Sign in / Sign up

Export Citation Format

Share Document