96 citations · 350 across the 21 of their papers we have counts for
21 papers
Synthesizing Programs with Continuous Optimization
Shantanu Mandal, Todd A. Anderson, Javier Turek +2
Automatic software generation based on some specification is known as program synthesis. Most existing approaches formulate program synthesis as a search problem with discrete para…
MP-CodeCheck: Evolving Logical Expression Code Anomaly Learning with Iterative Self-Supervision
Urs C. Muff, Celine Lee, Paul Gottschlich +1
Machine programming (MP) is concerned with automating software development. According to studies, software engineers spend upwards of 50% of their development time debugging softwa…
Simulation Intelligence: Towards a New Generation of Scientific Methods
Alexander Lavin, David Krakauer, Hector Zenil +21
The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of comput…
Toward Code Generation: A Survey and Lessons from Semantic Parsing
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…
ControlFlag: A Self-Supervised Idiosyncratic Pattern Detection System for Software Control Structures
Niranjan Hasabnis, Justin Gottschlich
Software debugging has been shown to utilize upwards of half of developers' time. Yet, machine programming (MP), the field concerned with the automation of software (and hardware)…
A Skew-Sensitive Evaluation Framework for Imbalanced Data Classification
Min Du, Nesime Tatbul, Brian Rivers +7
Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task. Metrics…
MISIM: A Neural Code Semantics Similarity System Using the Context-Aware Semantics Structure
Fangke Ye, Shengtian Zhou, Anand Venkat +10
Code semantics similarity can be used for many tasks such as code recommendation, automated software defect correction, and clone detection. Yet, the accuracy of such systems has n…
Learned Garbage Collection
Lujing Cen, Ryan Marcus, Hongzi Mao +3
Several programming languages use garbage collectors (GCs) to automatically manage memory for the programmer. Such collectors must decide when to look for unreachable objects to fr…
Software Language Comprehension using a Program-Derived Semantics Graph
Roshni G. Iyer, Yizhou Sun, Wei Wang +1
Traditional code transformation structures, such as abstract syntax trees (ASTs), conteXtual flow graphs (XFGs), and more generally, compiler intermediate representations (IRs), ma…
Context-Aware Parse Trees
Fangke Ye, Shengtian Zhou, Anand Venkat +8
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 pro…
An Abstraction-Based Framework for Neural Network Verification
Yizhak Yisrael Elboher, Justin Gottschlich, Guy Katz
Deep neural networks are increasingly being used as controllers for safety-critical systems. Because neural networks are opaque, certifying their correctness is a significant chall…
Learning Fitness Functions for Machine Programming
Shantanu Mandal, Todd A. Anderson, Javier S. Turek +3
The problem of automatic software generation is known as Machine Programming. In this work, we propose a framework based on genetic algorithms to solve this problem. Although genet…
MLSys: The New Frontier of Machine Learning Systems
Alexander Ratner, Dan Alistarh, Gustavo Alonso +66
Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains…
The Three Pillars of Machine Programming
Justin Gottschlich, Armando Solar-Lezama, Nesime Tatbul +6
In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research. Those pillars are: (i) intention…
Precision and Recall for Time Series
Nesime Tatbul, Tae Jun Lee, Stan Zdonik +2
Classical anomaly detection is principally concerned with point-based anomalies, those anomalies that occur at a single point in time. Yet, many real-world anomalies are range-base…
Precision and Recall for Range-Based Anomaly Detection
Tae Jun Lee, Justin Gottschlich, Nesime Tatbul +2
Classical anomaly detection is principally concerned with point-based anomalies, anomalies that occur at a single data point. In this paper, we present a new mathematical model to…
Greenhouse: A Zero-Positive Machine Learning System for Time-Series Anomaly Detection
Tae Jun Lee, Justin Gottschlich, Nesime Tatbul +2
This short paper describes our ongoing research on Greenhouse - a zero-positive machine learning system for time-series anomaly detection.
Toward Scalable Verification for Safety-Critical Deep Networks
Lindsey Kuper, Guy Katz, Justin Gottschlich +3
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. Form…
Paranom: A Parallel Anomaly Dataset Generator
Justin Gottschlich
In this paper, we present Paranom, a parallel anomaly dataset generator. We discuss its design and provide brief experimental results demonstrating its usefulness in improving the…
AI Programmer: Autonomously Creating Software Programs Using Genetic Algorithms
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 hu…
A Zero-Positive Learning Approach for Diagnosing Software Performance Regressions
Mejbah Alam, Justin Gottschlich, Nesime Tatbul +3
The field of machine programming (MP), the automation of the development of software, is making notable research advances. This is, in part, due to the emergence of a wide range of…