Semantic programming by example with pre-trained models
نویسندگان
چکیده
The ability to learn programs from few examples is a powerful technology with disruptive applications in many domains, as it allows users automate repetitive tasks an intuitive way. Existing frameworks on inductive synthesis only perform syntactic manipulations, where they rely the structure of given and not their meaning. Any semantic such transforming dates, have be manually encoded by designer programming framework. Recent advances large language models shown these very adept at performing transformations its input simply providing task hand. When comes transformations, however, are limited expressive power. In this paper, we propose novel framework for integrating few-shot learning combine strength two popular technologies. particular, tasked breaking down problem smaller subproblems, among which those that cannot solved syntactically passed model. We formalize three operators can integrated synthesizers. To minimize invoking expensive during learning, introduce deferred query execution algorithm considers oracles learning. evaluate our approach domain string transformations: combination methodology handled using either technologies themselves. Finally, demonstrate generality via case study profiling.
منابع مشابه
ImageNet pre-trained models with batch normalization
Convolutional neural networks (CNN) pre-trained on ImageNet are the backbone of most state-of-the-art approaches. In this paper, we present a new set of pretrained models with popular state-of-the-art architectures for the Caffe framework. The first release includes Residual Networks (ResNets) with generation script as well as the batch-normalization-variants of AlexNet and VGG19. All models ou...
متن کاملUnregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models
We show two important findings on the use of deep convolutional neural networks (CNN) in medical image analysis. First, we show that CNN models that are pre-trained using computer vision databases (e.g., Imagenet) are useful in medical image applications, despite the significant differences in image appearance. Second, we show that multiview classification is possible without the pre-registrati...
متن کاملQuery by Semantic Example
A solution to the problem of image retrieval based on queryby-semantic-example (QBSE) is presented. QBSE extends the idea of query-by-example to the domain of semantic image representations. A semantic vocabulary is first defined, and a semantic retrieval system is trained to label each image with the posterior probability of appearance of each concept in the vocabulary. The resulting vector is...
متن کاملNeural Programming by Example
Programming by Example (PBE) targets at automatically inferring a computer program for accomplishing a certain task from sample input and output. In this paper, we propose a deep neural networks (DNN) based PBE model called Neural Programming by Example (NPBE), which can learn from input-output strings and induce programs that solve the string manipulation problems. Our NPBE model has four neur...
متن کاملRobust Programming by Example
Robust programming lies at the heart of the type of coding called “secure programming”. Yet it is rarely taught in academia. More commonly, the focus is on how to avoid creating well-known vulnerabilities. While important, that misses the point: a well-structured, robust program should anticipate where problems might arise and compensate for them. This paper discusses one view of robust program...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ACM on programming languages
سال: 2021
ISSN: ['2475-1421']
DOI: https://doi.org/10.1145/3485477