Výsledky vyhledávání - "Chaudhari, Dipak"

Report

Neural Program Generation Modulo Static Analysis

Autor: Mukherjee, Rohan, Wen, Yeming, Chaudhari, Dipak, Reps, Thomas W., Chaudhuri, Swarat, Jermaine, Chris

State-of-the-art neural models of source code tend to be evaluated on the generation of individual expressions and lines of code, and commonly fail on long-horizon tasks such as the generation of entire method bodies. We propose to address this defic

Externí odkaz: http://arxiv.org/abs/2111.01633

Zobrazit plný text záznamu

Report

Meta-Meta Classification for One-Shot Learning

Autor: Chowdhury, Arkabandhu, Chaudhari, Dipak, Chaudhuri, Swarat, Jermaine, Chris

We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance and is sk

Externí odkaz: http://arxiv.org/abs/2004.08083

Zobrazit plný text záznamu

Report

HOUDINI: Lifelong Learning as Program Synthesis

Autor: Valkov, Lazar, Chaudhari, Dipak, Srivastava, Akash, Sutton, Charles, Chaudhuri, Swarat

We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and learning complex procedures are key challenges in lifelong learning. We s

Externí odkaz: http://arxiv.org/abs/1804.00218

Zobrazit plný text záznamu

Report

Building an IDE for the Calculational Derivation of Imperative Programs

Autor: Chaudhari, Dipak L., Damani, Om

Publikováno v: EPTCS 187, 2015, pp. 1-13

In this paper, we describe an IDE called CAPS (Calculational Assistant for Programming from Specifications) for the interactive, calculational derivation of imperative programs. In building CAPS, our aim has been to make the IDE accessible to non-exp

Externí odkaz: http://arxiv.org/abs/1508.03892

Zobrazit plný text záznamu

Report

Lexical Co-occurrence, Statistical Significance, and Word Association

Autor: Chaudhari, Dipak, Damani, Om P., Laxman, Srivatsan

Lexical co-occurrence is an important cue for detecting word associations. We present a theoretical framework for discovering statistically significant lexical co-occurrences from a given corpus. In contrast with the prevalent practice of giving weig

Externí odkaz: http://arxiv.org/abs/1008.5287

Zobrazit plný text záznamu