Different Conceptions of Learning: Function Approximation vs. Self-Organization

Wang, Pei; Li, Xiang

doi:10.1007/978-3-319-41649-6_14

Cited by 13 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even so, NARS is still related to the other AI theories and techniques here or there, and there are publications to compare NARS with the other techniques. For example, NARS has been compared with neural networks (Wang, 2006a;Wang and Li, 2016) and reinforcement learning (Wang and Hammer, 2015), which are related to the comment of Crosby and Shevlin (2020) on the relation between Deep Reinforcement Learning and Artificial Intelligence.…”

Section: Fruitfulnessmentioning

confidence: 99%

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Monett

Lewis²,

Þórisson

et al. 2020

Journal of Artificial General Intelligence

Self Cite

View full text Add to dashboard Cite

Pei Wang's paper titled "On Defining Artificial Intelligence" was published in a special issue of the Journal of Artificial General Intelligence (JAGI) in December of last year (Wang, 2019). Wang has been at the forefront of AGI research for over two decades. His non-axiomatic approach to reasoning has stood as a singular example of what may lie beyond narrow AI, garnering interest from NASA and Cisco, among others. We consider his article one of the strongest attempts, since the beginning of the field, to address the long-standing lack of consensus for how to define the field and topic of artificial intelligence (AI). In the recent AGISI survey on defining intelligence (Monett and Lewis, 2018), Pei Wang's definition, The essence of intelligence is the principle of adapting to the environment while working with insufficient knowledge and resources. Accordingly, an intelligent system should rely on finite processing capacity, work in real time, open to unexpected tasks, and learn from experience. This working definition interprets "intelligence" as a form of "relative rationality" (Wang, 2008), 1. Most striking in these numbers is the glaring absence of female authors. A common reason among female academics for rejecting our invitation to contribute was overcommitment. As a community, we may want to think of new, different ways of engaging the full spectrum of AI practitioners if we value inclusion as an essential constituent of a healthy scientific growth. Self determination and willingness to participate are also essential. This is an open access article licensed under the Creative Commons BY-NC-ND License.

show abstract

Section: Fruitfulnessmentioning

confidence: 99%

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Monett

Lewis²,

Þórisson

et al. 2020

Journal of Artificial General Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…One example is that in the current machine learning studies, "learning" has been commonly specified as the process of using a meta-algorithm (learning algorithm) to produce an object-level algorithm (model for a domain problem) according to the training data (Flach, 2012). This working definition is exact and simple, as well as fruitful in many domains, though is arguably only a restricted version if compared to the learning processes in the human mind (Wang and Li, 2016), even compared to the initial diverse approaches within the field (Michalski, Carbonell, and Mitchell, 1984).…”

Section: Function-aimentioning

confidence: 99%

On Defining Artificial Intelligence

Wang

2019

Journal of Artificial General Intelligence

Self Cite

305

140

View full text Add to dashboard Cite

This article systematically analyzes the problem of defining “artificial intelligence.” It starts by pointing out that a definition influences the path of the research, then establishes four criteria of a good working definition of a notion: being similar to its common usage, drawing a sharp boundary, leading to fruitful research, and as simple as possible. According to these criteria, the representative definitions in the field are analyzed. A new definition is proposed, according to it intelligence means “adaptation with insufficient knowledge and resources.” The implications of this definition are discussed, and it is compared with the other definitions. It is claimed that this definition sheds light on the solution of many existing problems and sets a sound foundation for the field.

show abstract

“…A cumulative learner in our conceptualization is a learning controller [22] that, guided by one or more top-level internalized goals (or drives), implements a cumulative modeling process whereby regularities are recursively extracted from the learner's experience (of self and environment) to construct integrated models useful for achieving goals [3,22]. The collection of models form a unified body of knowledge that can be used, by a set of additional and appropriate management processes (see Aa-f above), as the basis for making predictions about, and achieving goals with respect to, an environment, and that can be used to improve future learning-in speed, quality, efficiency, or all of these [28]. At the risk of oversimplification, a compact definition of cumulative learning might read something like "using a unified body of knowledge to continually and recursively integrate new information from many contexts into that body."…”

Section: Functions Of Cumulative Learningmentioning

confidence: 99%

“…An extreme case of this is using analogies to deepen or broaden knowledge of a set of phenomena. In NARS, for instance, learning involves not only tasks but also effective (re-)organization of knowledge, without respect to specific problems, so that it may later be used on any relevant task [28] (cf. Ae, Af).…”

Section: Generalitymentioning

confidence: 99%

Cumulative Learning

Þórisson

Bieger

et al. 2019

Artificial General Intelligence

Self Cite

View full text Add to dashboard Cite

An important feature of human learning is the ability to continuously accept new information and unify it with existing knowledge, a process that proceeds largely automatically and without catastrophic side-effects. A generally intelligent machine (AGI) should be able to learn a wide range of tasks in a variety of environments. Knowledge acquisition in partially-known and dynamic task-environments cannot happen all-at-once, and AGI-aspiring systems must thus be capable of cumulative learning: efficiently making use of existing knowledge while learning new things, increasing the scope of ability and knowledge incrementally-without catastrophic forgetting or damaging existing skills. Many aspects of such learning have been addressed in artificial intelligence (AI) research, but relatively few examples of cumulative learning have been demonstrated to date and no generally accepted explicit definition exists of this category of learning. Here we provide a general definition of cumulative learning and describe how it relates to other concepts frequently used in the AI literature.

show abstract

Different Conceptions of Learning: Function Approximation vs. Self-Organization

Cited by 13 publications

References 9 publications

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

Special Issue “On Defining Artificial Intelligence”—Commentaries and Author’s Response

On Defining Artificial Intelligence

Cumulative Learning

Contact Info

Product

Resources

About