Neuro-Symbolic Program Synthesis
نویسندگان
چکیده
Recent years have seen the proposal of a number of neural architectures for the problem of Program Induction. Given a set of input-output examples, these architectures are able to learn mappings that generalize to new test inputs. While achieving impressive results, these approaches have a number of important limitations: (a) they are computationally expensive and hard to train, (b) a model has to be trained for each task (program) separately, and (c) it is hard to interpret or verify the correctness of the learnt mapping (as it is defined by a neural network). In this paper, we propose a novel technique, Neuro-Symbolic Program Synthesis, to overcome the above-mentioned problems. Once trained, our approach can automatically construct computer programs in a domain-specific language that are consistent with a set of input-output examples provided at test time. Our method is based on two novel neural modules. The first module, called the cross correlation I/O network, given a set of input-output examples, produces a continuous representation of the set of I/O examples. The second module, the RecursiveReverse-Recursive Neural Network (R3NN), given the continuous representation of the examples, synthesizes a program by incrementally expanding partial programs. We demonstrate the effectiveness of our approach by applying it to the rich and complex domain of regular expression based string transformations. Experiments show that the R3NN model is not only able to construct programs from new input-output examples, but it is also able to construct new programs for tasks that it had never observed before during training.
منابع مشابه
Neuro-ACT Cognitive Architecture Applications in Modeling Driver’s Steering Behavior in Turns
Cognitive Architectures (CAs) are the core of artificial cognitive systems. A CA is supposed to specify the human brain at a level of abstraction suitable for explaining how it achieves the functions of the mind. Over the years a number of distinct CAs have been proposed by different authors and their limitations and potentials were investigated. These CAs are usually classified as symbolic and...
متن کاملSHERLOCK - An Inteface for Neuro-Symbolic Networks∗
We propose SHERLOCK a novel problemsolving application based on neuro-symbolic networks. The application takes a knowledge base and rules in the form of a logic program, and compiles it into a connectionist neural network that performs computations. The network’s output signal is then translated back into logical form. SHERLOCK allows to compile logic programs either to classical neuro-symbolic...
متن کاملQ-SATyrus: Mapping Neuro-symbolic Reasoning into an Adiabatic Quantum Computer
Much has been promised about quantum computing accelerators, but few actual commercial technologies have been made available so far. The DWave Computers Series constitutes one family of adiabatic quantum computers, based on energy minimization techniques that are considered suitable for solving discrete optimization problems. This work shows a path to explore these machines in order to perform ...
متن کاملTitle of dissertation : FRAMEWORK SYNTHESIS FOR SYMBOLIC EXECUTION OF EVENT - DRIVEN FRAMEWORKS
Title of dissertation: FRAMEWORK SYNTHESIS FOR SYMBOLIC EXECUTION OF EVENT-DRIVEN FRAMEWORKS Jinseong Jeon, Doctor of Philosophy, 2016 Dissertation directed by: Professor Jeffrey S. Foster Department of Computer Science Symbolic execution is a powerful program analysis technique, but it is very challenging to apply to programs built using event-driven frameworks, such as Android. The main reaso...
متن کاملFramework synthesis for Symbolic Execution of Event-Driven Frameworks
Title of dissertation: FRAMEWORK SYNTHESIS FOR SYMBOLIC EXECUTION OF EVENT-DRIVEN FRAMEWORKS Jinseong Jeon, Doctor of Philosophy, 2016 Dissertation directed by: Professor Jeffrey S. Foster Department of Computer Science Symbolic execution is a powerful program analysis technique, but it is very challenging to apply to programs built using event-driven frameworks, such as Android. The main reaso...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1611.01855 شماره
صفحات -
تاریخ انتشار 2016