Mapping the limits of perceptrons

A mathematical analysis clarified limitations of restricted perceptron architectures.

Marvin Minsky and Seymour Papert

AI topics

Explore related entries. Larger tags appear on more entries.

The contribution

Minsky and Papert examined which properties certain perceptron systems could compute. The book is included as a foundational research monograph because its precise questions about representation and computational limits are central to the history of neural networks.

What this does not establish

Its results do not disprove the usefulness of all neural networks. Nor does this source establish that one book alone caused an AI funding winter.

Why this date?

1969 is the original edition, not the later expanded edition.

This entry follows the linked publication. Read the source and date conventions.

The original work

Perceptrons: An Introduction to Computational Geometry

Authors: Marvin Minsky and Seymour Papert
Publication: MIT Press, original edition
Source type: Research monograph

Original edition publisher record

The links above support the description and dating of this entry. Full text may be open or publisher-restricted.

Cited By

Atlas entries whose reference lists cite this work or the publication version noted below.

Neural networks and physical systems with emergent collective computational abilities (1982)
Listed in the source bibliography. Check the reference list.
Learning representations by back-propagating errors (1986)
Reference 2 cites Minsky and Papert, Perceptrons (MIT, 1969). Check the reference list.
The Utility Driven Dynamic Error Propagation Network (1987)
Listed in the source bibliography. Check the reference list.
Multilayer feedforward networks are universal approximators (1989)
Cites Minsky and Papert (1969), Perceptrons. The extracted title has an OCR spelling error. Check the reference list.

Citations

Works in the Atlas cited by this entry.

A logical calculus of the ideas immanent in nervous activity (1943)
Bibliographic Notes cite the 1943 paper. The printed citation changes the title ending to neural nets and gives page 137 instead of 133. Checked in the 1988 edition retaining the original text. Check the reference list.
The Organization of Behavior: A Neuropsychological Theory (1949)
Bibliographic Notes cite the 1949 book; checked in the 1988 edition retaining the original text. Check the reference list.

Bibliography coverage: Reference section indexed. Open the source.

The accessible scan is the 1988 expanded edition, which retains the original text with the authors' 1972 handwritten corrections. Bibliographic facts have been extracted from the entire Bibliographic Notes section; the surrounding critical essay is not reproduced. Later handwritten references are separated from the original references. Unclear handwritten metadata is explicitly marked and is not used to create Atlas links. This is edition-qualified coverage, not a claim that the 1969 first printing contains the later additions.

Read the indexed bibliography

Bibliographic Notes: cited works, printed pages 281-287

Rosenblatt, F. (1959). Two theorems of statistical separability in the perceptron. Proceedings of a Symposium on the Mechanization of Thought Processes. HMSO, London, 421-456. Rosenblatt, F. (1962). Principles of Neurodynamics. Spartan Books, New York. Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of Research and Development 3(3), 210-223. Samuel, A. L. (1967). Some studies in machine learning using the game of checkers, Part II. IBM Journal of Research and Development 11(4), 601-618. Palmieri, G., and Sanna, R. (1960). Methodos 12(48). [Title not supplied in the source.] Gamba, A., Gamberini, L., Palmieri, G., and Sanna, R. (1961). Further experiments with PAPA. Nuovo Cimento Supplement 2, volume 20, 221-231. Ashby, W. R. (1952). Design for a Brain. Wiley, New York. [Mentioned twice in the notes.] Clark, W. A., and Farley, B. G. (1955). Generalization of pattern-recognition in a self-organizing system. Proceedings of the Western Joint Computer Conference, 85-111. Minsky, M. (1954). Neural nets and the brain-model problem. Doctoral dissertation, Princeton University. [Year as printed.] Uttley, A. M. (1956). Conditional probability machines. Automata Studies. Princeton University, 253-285. Agmon, S. (1954). The relaxation method for linear inequalities. Canadian Journal of Mathematics 6(3), 382-392. Block, H. D. (1962). The perceptron: a model for brain functioning. Reviews of Modern Physics 34(1), 123-135. Papert, S. (1961). Some Mathematical Models of Learning. Proceedings of the Fourth London Symposium on Information Theory, C. Cherry (ed.). Academic Press, New York. Nilsson, N. (1965). Learning Machines. McGraw-Hill, New York. Minsky, M., and Selfridge, O. G. (1961). Learning in neural nets. Proceedings of the Fourth London Symposium on Information Theory, C. Cherry (ed.). Academic Press, New York. Selfridge, O. G. (1956). Pattern recognition and learning. Proceedings of the Third London Symposium on Information Theory. Academic Press, New York, 345. Lettvin, J. Y., Maturana, H., McCulloch, W. S., and Pitts, W. (1959). What the frog's eye tells the frog's brain. Proceedings of the IRE 47, 1940-1951. Hubel, D. H., and Wiesel, T. N. (1959). Receptive fields of single neurons in the cat's striate cortex. Journal of Physiology 148, 574-591. Pitts, W., and McCulloch, W. S. (1947). How we know universals. Bulletin of Mathematical Biophysics 9, 127-147. McCulloch, W. S. (1965). Embodiments of Mind. MIT Press, Cambridge, Massachusetts. McCulloch, W. S., and Pitts, W. (1943). A logical calculus of the ideas immanent in neural nets. Bulletin of Mathematical Biophysics 5, 115-137. [Title wording and last page are as printed; the original article has a different title ending and ends on page 133.] Minsky, M. (1967). Computation: Finite and Infinite Machines. Prentice-Hall, Englewood Cliffs, New Jersey. Tinbergen, N. (1951). The Study of Instinct. Oxford, New York. Bledsoe, W. W., and Browning, I. (1959). Pattern recognition and reading by machine. Proceedings of the Eastern Joint Computer Conference, 225-232. Roberts, L. G. (1960). Pattern recognition with an adaptive network. IRE International Convention Record, part II, 66-70. Rosenblatt, F. (1960). Perceptual generalization over transformation groups. Self-Organizing Systems. Pergamon Press, New York, 63-96. Dertouzos, M. (1965). Threshold Logic: A Synthesis Approach. MIT Press, Cambridge, Massachusetts. Myhill, J., and Kautz, W. H. (1961). On the size of weights required for linear-input switching functions. IRE Transactions on Electronic Computers 10(2), 288-290. Muroga, S., and Toda, I. (1966). Lower bounds on the number of threshold functions. IEEE Transactions on Electronic Computers EC-15(5), 805-806. Muroga, S. (1965). Lower bounds on the number of threshold functions and a maximum weight. IEEE Transactions on Electronic Computers EC-14(2), 136-148. Feigenbaum, E. A., and Feldman, J. (1963). Computers and Thought. McGraw-Hill, New York. Minsky, M. (1968). Semantic Information Processing. MIT Press, Cambridge, Massachusetts. Newell, A., Shaw, J. C., and Simon, H. A. (1959). Report on a general problem-solving program. Proceedings of the International Conference on Information Processing, UNESCO House, 256-264. Guzman, A. (1968). Decomposition of a visual scene into bodies. Proceedings of the Fall Joint Computer Conference. Hebb, D. O. (1949). The Organization of Behavior. Wiley, New York.

Handwritten additions from the 1972 printing

Block, H. D. (1970). A Review of Perceptrons. Information and Control 17. [The handwritten page range is not reliably legible in the available transcription.] Newell, A. (1969). A step toward the understanding of information processes. Science 165, August 1969. [The handwritten date and page range are not reliably legible in the available transcription.] Mycielski, J. (1972). Review of Perceptrons. Bulletin of the American Mathematical Society 78(1), 12-15. DOI: 10.1090/S0002-9904-1972-12831-3. Minsky, M., and Papert, S. Re-View of Perceptrons. AI Memo, Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts. [Memo number appears as 293 in the transcription and remains unverified.]

Download the bibliography index · Download Atlas citation links

These links cover verified matches within the Atlas. They are not total scholarly citation counts. A citation alone does not establish that the later system implements the same method.

AI topics

The contribution

What this does not establish

Why this date?

Comments