“When David Marr at MIT moved into computer vision, he generated a lot of excitement, but he hit up against the problem of knowledge representation; he had no good representations for knowledge in his vision systems.”

—  Marvin Minsky

Marvin Minsky in: David G. Stork (1998). HAL's Legacy: 2001's Computer As Dream and Reality. p. 16

Adopted from Wikiquote. Last update June 3, 2021. History

Help us to complete the source, original and additional information

Do you have more details about the quote "When David Marr at MIT moved into computer vision, he generated a lot of excitement, but he hit up against the problem …" by Marvin Minsky?
Marvin Minsky photo
Marvin Minsky 65
American cognitive scientist 1927–2016

Related quotes

Eric R. Kandel photo

“Unlike vision, touch, or smell, which are prewired and based on Kantian a priori knowledge, the spatial map presents us with a new type of representation, one based on a combination of a priori knowledge and learning.”

Eric R. Kandel (1929) American neuropsychiatrist

In Search of Memory (2006)
Context: Unlike vision, touch, or smell, which are prewired and based on Kantian a priori knowledge, the spatial map presents us with a new type of representation, one based on a combination of a priori knowledge and learning. The general capability for forming spatial maps is built into the mind, but the particular map is not. Unlike neurons in a sensory system, place cells are not switched on by sensory stimulation. Their collective activity represents the location where the animal thinks it is.

John McCarthy photo

“Intelligence has two parts, which we shall call the epistemological and the heuristic. The epistemological part is the representation of the world in such a form that the solution of problems follows from the facts expressed in the representation. The heuristic part is the mechanism that on the basis of the information solves the problem and decides what to do.
[…]
The right way to think about the general problems of metaphysics and epistemology is not to attempt to clear one's own mind of all knowledge and start with 'Cogito ergo sum' and build up from there. Instead, we propose to use all of our knowledge to construct a computer program that knows. The correctness of our philosophical system will be tested by numerous comparisons between the beliefs of the program and our own observations and knowledge.”

John McCarthy (1927–2011) American computer scientist and cognitive scientist

John McCarthy and Patrick J. Hayes. " Some Philosophical Problems from the Standpoint of Artificial Intelligence http://www-formal.stanford.edu/jmc/mcchay69.html", Sect. 2.1, Machine Intelligence 4, ed. Donald Michie (Elsevier, 1969), p. 463 ff., ISBN 0444197443
1960s

“The representation of knowledge in symbolic form is a matter that has pre-occupied the world of documentation since its origin. The problem is now relevant in many situations other than documents and indexes. The structure of records and files in databases: data structures in computer programming; the syntactic and semantic structure of natural language; knowledge representation in artificial intelligence; models of human memory: in all these fields it is necessary to decide how knowledge may be represented so that the representations may be manipulated.”

Brian Campbell Vickery (1918–2009) British information theorist

As cited in: Lyn Robinson and David Bawden (2011).
Concepts of documentation (1978)

Roberto Durán photo

“He’s good inside, very good, strong physically. The one thing that surprised me the most was his quickness. And his defensive ability. He moves his head a lot, feints a lot. He’s not an easy man to hit.”

Roberto Durán (1951) Panamanian boxer

Carlos Palomino, 16 June 1980, after his defeat by Duran http://coxscorner.tripod.com/duran.html
About Durán

Israel Kirzner photo

“A piece of knowledge about boat-building, about whose correctness Crusoe has no doubts at all, will not be seen as a hunch and will be valued according to Menger's Law. It may be said that Crusoe is well aware that he possesses this kind of information; he will deploy and value it in the same way as he may be imagined to deploy and value other resources he believes are definitely at his disposal. But concerning Crusoe's hunches and his visions in the face of a changing, uncertain environment, it cannot be said at all that Crusoe knows he has a hunch or a vision of the future. He does not act by deliberately utilizing his hunch about the future; instead, he finds that his actions reflect his hunches…In other words, it turns out, the essence of entrepreneurial vision, and what sets it apart from knowledge as a resource, is reflected in Crusoe's lack of self-consciousness concerning it…Crusoe may…gradually come to be aware of his vision. When he does, that vision ceases to be entrepreneurial and comes to be a resource. Moreover, Crusoe's realization that he possesses this definite information resource may itself be entrepreneurial. As soon as he 'knows' that he possesses an item of knowledge, that item ceases to correspond to entrepreneurial vision; instead, as with all resources, it is Crusoe's belief that he has the resources at his disposal that may now constitute his entrepreneurial hunch.”

Israel Kirzner (1930) American economist

Israel Kirzner, (1979: 168-169); as cited in: " Israel Kirzner's Entrepreneurship http://www.constitution.org/pd/gunning/subjecti/workpape/kirz_ent.pdf" by the Constitution Society, May 31, 2004

Herbert A. Simon photo

“We distinguish diagrammatic from sentential paper-and-pencil representations of information by developing alternative models of information-processing systems that are informationally equivalent and that can be characterized as sentential or diagrammatic. Sentential representations are sequential, like the propositions in a text. Diagrammatic representations are indexed by location in a plane. Diagrammatic representations also typically display information that is only implicit in sentential representations and that therefore has to be computed, sometimes at great cost, to make it explicit for use. We then contrast the computational efficiency of these representations for solving several. illustrative problems in mathematics and physics.”

Herbert A. Simon (1916–2001) American political scientist, economist, sociologist, and psychologist

Source: 1980s and later, "Why a diagram is (sometimes) worth ten thousand words," (1987), p. 65

Jean-Paul Marat photo

“Robespierre listened to me with terror. He grew pale and silent for some time. This interview confirmed me in the opinion that I always had of him, that he unites the knowledge of a wise senator with the integrity of a thoroughly good man and the zeal of a true patriot but that he is lacking as a statesman in clearness of vision and determination.”

Jean-Paul Marat (1743–1793) politician and journalist during the French Revolution

L'Ami du peuple, vol. 7, p. 3965

Francis Heylighen photo

“(Systems science) does not aim to find the one true representation for a given type of systems (e. g. physical, chemical or biological systems), but to formulate general principles about how different representations of different systems can be constructed so as to be effective in problem-solving.”

Francis Heylighen (1960) Belgian cyberneticist

Francis Heylighen, 1990, "Classical and non-classical representations in physics I." Cybernetics and Systems 21. p. 423; As cited by: Hieronymi, A. (2013), Understanding Systems Science: A Visual and Integrative Approach. Syst. Res.. doi: 10.1002/sres.2215

“The representational nature of maps, however, is often ignored – what we see when looking at a map is not the word, but an abstract representation that we find convenient to use in place of the world. When we build these abstract representations we are not revealing knowledge as much as are creating it.”

Alan MacEachren (1952) American geographer

(2004), p. v
How Maps Work: Representation, Visualization, and Design (1995)

“Tracking the individual learning curves of the major technologies that comprise the infrastructure of information technology provides a more detailed account of the present and future state-of-the art of the technologies underlying convergence. The base technologies of digital electronics, general-purpose computer architectures, software and interaction are mature and provide solid foundations for computer science. The upper technologies of knowledge representation and acquisition, autonomy and sociality, support product innovation and provide the beginnings of foundations for knowledge science. Well's dream of a world brain making available all of human knowledge is well on its way to realization and it is in the representation, acquisition, and access and effective application of that knowledge that the commercial potential and socio-economic impact of convergence lies.”

Brian R. Gaines (1938) British computer scientist

Last paragraph
Convergence to the Information Highway (1996)

Related topics