Search Results for author: Justin Gottschlich

Found 19 papers, 5 papers with code

Toward Code Generation: A Survey and Lessons from Semantic Parsing

no code implementations26 Apr 2021 Celine Lee, Justin Gottschlich, Dan Roth

With the growth of natural language processing techniques and demand for improved software engineering efficiency, there is an emerging interest in translating intention from human languages to programming languages.

Code Generation Program Synthesis +1

Class-Weighted Evaluation Metrics for Imbalanced Data Classification

no code implementations12 Oct 2020 Akhilesh Gupta, Nesime Tatbul, Ryan Marcus, Shengtian Zhou, Insup Lee, Justin Gottschlich

Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task.

General Classification

Software Language Comprehension using a Program-Derived Semantics Graph

no code implementations NeurIPS Workshop CAP 2020 Roshni G. Iyer, Yizhou Sun, Wei Wang, Justin Gottschlich

To continue to advance this research, we present the program-derived semantics graph, a new graphical structure to capture semantics of code.

Context-Aware Parse Trees

no code implementations24 Mar 2020 Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Paul Petersen, Jesmin Jahan Tithi, Tim Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich

The simplified parse tree (SPT) presented in Aroma, a state-of-the-art code recommendation system, is a tree-structured representation used to infer code semantics by capturing program \emph{structure} rather than program \emph{syntax}.

An Abstraction-Based Framework for Neural Network Verification

1 code implementation31 Oct 2019 Yizhak Yisrael Elboher, Justin Gottschlich, Guy Katz

In this paper, we propose a framework that can enhance neural network verification techniques by using over-approximation to reduce the size of the network - thus making it more amenable to verification.

The Three Pillars of Machine Programming

no code implementations20 Mar 2018 Justin Gottschlich, Armando Solar-Lezama, Nesime Tatbul, Michael Carbin, Martin Rinard, Regina Barzilay, Saman Amarasinghe, Joshua B. Tenenbaum, Tim Mattson

In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research.

Precision and Recall for Time Series

4 code implementations NeurIPS 2018 Nesime Tatbul, Tae Jun Lee, Stan Zdonik, Mejbah Alam, Justin Gottschlich

Classical anomaly detection is principally concerned with point-based anomalies, those anomalies that occur at a single point in time.

Anomaly Detection General Classification +2

Toward Scalable Verification for Safety-Critical Deep Networks

no code implementations18 Jan 2018 Lindsey Kuper, Guy Katz, Justin Gottschlich, Kyle Julian, Clark Barrett, Mykel Kochenderfer

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability.

Autonomous Driving

Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection

no code implementations9 Jan 2018 Tae Jun Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik

This short paper describes our ongoing research on Greenhouse - a zero-positive machine learning system for time-series anomaly detection.

Anomaly Detection Time Series

Precision and Recall for Range-Based Anomaly Detection

no code implementations9 Jan 2018 Tae Jun Lee, Justin Gottschlich, Nesime Tatbul, Eric Metcalf, Stan Zdonik

Classical anomaly detection is principally concerned with point-based anomalies, anomalies that occur at a single data point.

Anomaly Detection

AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms

1 code implementation17 Sep 2017 Kory Becker, Justin Gottschlich

In this paper, we present the first-of-its-kind machine learning (ML) system, called AI Programmer, that can automatically generate full software programs requiring only minimal human guidance.

Cannot find the paper you are looking for? You can Submit a new open access paper.