#### Filter Results:

- Full text PDF available (59)

#### Publication Year

1973

2016

- This year (0)
- Last 5 years (7)
- Last 10 years (21)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Leslie G. Valiant
- Commun. ACM
- 1984

Humans appear to be able to learn new concepts without needing to be programmed explicitly in any conventional sense. In this paper we regard learning as the phenomenon of knowledge acquisition in the absence of explicit programming. We give a precise methodology for studying this phenomenon from a computational viewpoint. It consists of choosing anā¦ (More)

- Leslie G. Valiant
- Commun. ACM
- 1990

The success of the von Neumann model of sequential computation is attributable to the fact that it is an efficient bridge between software and hardware: high-level languages can be efficiently compiled on to this model; yet it can be effeciently implemented in hardware. The author argues that an analogous bridge between software and hardware in required forā¦ (More)

- Leslie G. Valiant
- Theor. Comput. Sci.
- 1979

Ati&. It is shown that the permanent function of (0, I)-matrices is a complete problem for the class of counting problems associated with nondeterministic polynomial time computations. Related counting problems are also considered. The reductions used are characterized by their nontrivial use of arithmetic.

- Leslie G. Valiant, Vijay V. Vazirani
- STOC
- 1985

For all known NP-complete problems the number of solutions in instances having solutions may vary over an exponentially large range. Furthermore, most of the well-known ones, such as satisfiability, are parsimoniously interreducible, and these can have any number of solutions between zero and an exponentially large number. It is natural to ask whether theā¦ (More)

- Leslie G. Valiant
- SIAM J. Comput.
- 1979

- Leslie G. Valiant
- STOC
- 1979

In the theory of recursive functions and computational complexity it has been demonstrated repeatedly that the natural problems tend to cluster together in “completeness classes”. These are families of problems that (A) are <underline>computationally</underline> interreducible and (B) are the hardest members of someā¦ (More)

- Leonard Pitt, Leslie G. Valiant
- J. ACM
- 1988

The computational complexity of learning Boolean concepts from examples is investigated. It is shown for various classes of concept representations that these cannot be learned feasibly in a distribution-free sense unless R = NP. These classes include (a) disjunctions of two monomials, (b) Boolean threshold functions, and (c) Boolean formulas in which eachā¦ (More)

- Michael Kearns, Leslie G. Valiant
- J. ACM
- 1989

In this paper, we prove the intractability of learning several classes of Boolean functions in the distribution-free model (also called the Probably Approximately Correct or PAC model) of learning from examples. These results are <italic>representation independent</italic>, in that they hold regardless of the syntactic form in which the learner chooses toā¦ (More)

- Leslie G. Valiant
- FOCS
- 2004

- Leslie G. Valiant
- MFCS
- 1977