Filters








14,608 Hits in 5.9 sec

Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic [article]

Thibault Gauthier
2020 arXiv   pre-print
The paper describes a deep reinforcement learning framework based on self-supervised learning within the proof assistant HOL4.  ...  In this case, a Monte Carlo Tree Search (MCTS) algorithm guided by a TNN can be used to explore the search space and produce better examples for training the next TNN.  ...  Deep Reinforcement Learning When possible, the deep reinforcement learning approach [41] is preferable to a supervised learning approach for two main reasons. First, an oracle is not required.  ... 
arXiv:1910.11797v3 fatcat:bqtdfbrcxrcc5p6e3tzygogxsy

Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic

Thibault Gauthier
unpublished
The paper describes a deep reinforcement learning framework based on self-supervised learning within the proof assistant HOL4.  ...  In this case, a Monte Carlo Tree Search (MCTS) algorithm guided by a TNN can be used to explore the search space and produce better examples for training the next TNN.  ...  Deep Reinforcement Learning When possible, the deep reinforcement learning approach [41] is preferable to a supervised learning approach for two main reasons. First, an oracle is not required.  ... 
doi:10.29007/7jmg fatcat:skbzeodwg5gefo4trnr2hiigja

Neural-Guided Inductive Synthesis of Functional Programs on List Manipulation by Offline Supervised Learning

Yuhong Wang, Xin Li
2021 IEEE Access  
To practically manipulate data structures of lists, our method synthesizes functional programs with popular higher-order combinators including map, foldl and foldr.  ...  Our approach targets an easy and effective integration of deep learning techniques in making better PBE systems and combines two technical ideas on generating diverse training dataset and designing rich  ...  ACKNOWLEDGMENT The authors would like to thank Zhenjiang Hu and Jian Guo for their valuable suggestions and comments and Lisa Zhang for sharing her tools and benchmarks.  ... 
doi:10.1109/access.2021.3079351 fatcat:gpo4rewcxjdqbdakbnllgtfgei

Logic and Learning (Dagstuhl Seminar 19361)

Michael Benedikt, Kristian Kersting, Phokion G. Kolaitis, Daniel Neider, Michael Wagner
2020 Dagstuhl Reports  
The three focal points of the seminar were the strands of "Logic for Machine Learning", "Machine Learning for Logic", and "Logic vs. Machine Learning".  ...  It would be fruitful to look for common techniques in applying learning to logic-related tasks, which requires looking across a wide spectrum of applications.  ...  There is a growing need to enable the disparate communities of logic and learning to interact with each other, and we noted from the seminar that researchers from each community appreciated the perspective  ... 
doi:10.4230/dagrep.9.9.1 dblp:journals/dagstuhl-reports/BenediktKKN19 fatcat:rwjks5mydzhctlvedtel3vtzoy

CNN2Gate: An Implementation of Convolutional Neural Networks Inference on FPGAs with Automated Design Space Exploration

Alireza Ghaffari, Yvon Savaria
2020 Electronics  
Furthermore, it writes this information in the proper format for the FPGA vendor's OpenCL synthesis tools that are then used to build and run the project on FPGA.  ...  Because of the research efforts put into topics, such as architecture, synthesis, and optimization, some new challenges are arising for integrating suitable hardware solutions to high-level machine learning  ...  Abbreviations The following abbreviations are used in this manuscript:  ... 
doi:10.3390/electronics9122200 fatcat:ztmdkq75pjbmril5klx6tnbz7m

CNN2Gate: Toward Designing a General Framework for Implementation of Convolutional Neural Networks on FPGA [article]

Alireza Ghaffari, Yvon Savaria
2020 arXiv   pre-print
CNN2Gate performs design-space exploration using a reinforcement learning agent and fits the design on different FPGAs with limited logic resources automatically.  ...  Furthermore, it writes this information in the proper format for OpenCL synthesis tools that are then used to build and run the project on FPGA.  ...  for various FPGA devices using a hardware-aware reinforcement learning algorithm. • Synthesizing and running the project on FPGA.  ... 
arXiv:2004.04641v2 fatcat:zu6dxff2urg57ejzrn4ac2jkha

DRiLLS: Deep Reinforcement Learning for Logic Synthesis [article]

Abdelrahman Hosny, Soheil Hashemi, Mohamed Shalan, Sherief Reda
2019 arXiv   pre-print
In this work, we propose a novel reinforcement learning-based methodology that navigates the optimization space without human intervention.  ...  Logic synthesis requires extensive tuning of the synthesis optimization flow where the quality of results (QoR) depends on the sequence of optimizations used.  ...  ), a novel framework based on reinforcement learning developed for generating logic synthesis optimization flows.  ... 
arXiv:1911.04021v2 fatcat:m5yvlqzkwrfo5przeacvs6taaa

Online Reinforcement Learning for Self-adaptive Information Systems [chapter]

Alexander Palm, Andreas Metzger, Klaus Pohl
2020 Lecture Notes in Computer Science  
Online reinforcement learning (RL) addresses design time uncertainty by learning the effectiveness of adaptation actions through interactions with the system's environment at run time, thereby automating  ...  However, developing self-adaptation logic may be difficult due to design time uncertainty; e.g., anticipating all potential environment changes at design time is in most cases infeasible.  ...  We cordially thank Claas Keller, Tristan Kley and Jan Löber for supporting us in carrying out the experiments, Zoltan Mann for comments on earlier versions of the paper, as well as the anonymous reviewers  ... 
doi:10.1007/978-3-030-49435-3_11 fatcat:ebl2mtyzyzd67keui7lmah7yqi

Automatic Face Aging in Videos via Deep Reinforcement Learning

Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Nghia Nguyen, Eric Patterson, Tien D. Bui, Ngan Le
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper presents a novel approach to synthesize automatically age-progressed facial images in video sequences using Deep Reinforcement Learning.  ...  The approach is optimized using a long-term reward, Reinforcement Learning function with deep feature extraction from Deep Convolutional Neural Network.  ...  Contributions of this work: This paper presents a deep Reinforcement Learning (RL) approach to Video Age Progression to guarantee the consistency of aging patterns in synthesized faces captured in videos  ... 
doi:10.1109/cvpr.2019.01025 dblp:conf/cvpr/DuongLQNPBL19 fatcat:hu4vsncasrgfzmtdzfq4jpkvgy

Recent Advances in Neural Program Synthesis [article]

Neel Kant
2018 arXiv   pre-print
In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence.  ...  The successes in these problems has led researchers to consider the possibilities for intelligent systems to tackle a problem that humans have only recently themselves considered: program synthesis.  ...  The key idea is that the NPI is capable of abstraction and higher-order controls over the program. When a new function is called with arguments, it is expressed in an embedding vector.  ... 
arXiv:1802.02353v1 fatcat:klvndhzs6vbjfjhizsqg4xexym

AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning [article]

Qijing Huang, Ameer Haj-Ali, William Moses, John Xiang, Ion Stoica, Krste Asanovic, John Wawrzynek
2020 arXiv   pre-print
In this paper, we evaluate a new technique to address the phase-ordering problem: deep reinforcement learning.  ...  Furthermore, unlike existing state-of-the-art solutions, our deep reinforcement learning solution shows promising result in generalizing to real benchmarks and 12,874 different randomly generated programs  ...  ACKNOWLEDGEMENT This research is supported in part by NSF CISE Expeditions Award CCF-1730628, the Defense Advanced Research  ... 
arXiv:2003.00671v2 fatcat:xemglojhkfhllo7oeo4aosqala

Field-Programmable Deep Neural Network (DNN) Learning and Inference accelerator: a concept [article]

Luiz M Franca-Neto
2018 arXiv   pre-print
Reconfigurability attends diverse DNN designs and allows for different number of workers to be assigned to different layers as a function of the relative difference in computational load among layers.  ...  A Field-Programmable DNN learning and inference accelerator (FProg-DNN) using hybrid systolic and non-systolic techniques, distributed information-control and deep pipelined structure is proposed and its  ...  Field-Programmable DNN Learning & Inference Accelerator (FProg-DNN) presented in this work aims at providing for reconfigurable DNNs what FPGAs offer for reconfigurable logic.  ... 
arXiv:1802.04899v4 fatcat:xngvmzmz6bavvglgqyi6yjkxvy

Safe Reinforcement Learning via Shielding [article]

Mohammed Alshiekh, Roderick Bloem, Ruediger Ehlers, Bettina Könighofer, Scott Niekum, Ufuk Topcu
2017 arXiv   pre-print
To this end, given the temporal logic specification that is to be obeyed by the learning system, we propose to synthesize a reactive system called a shield.  ...  We introduce a new approach to learn optimal policies while enforcing properties expressed in temporal logic.  ...  .: Correct-by-synthesis reinforcement learning with temporal logic constraints. In: IROS 2015, Germany, Sep. 28 - Oct. 2, 2015. pp. 4983–4990 (2015) 24.  ... 
arXiv:1708.08611v2 fatcat:4zrfgcwbtvgalanluya6plemr4

Cognification of Program Synthesis—A Systematic Feature-Oriented Analysis and Future Direction

Ahmad F. Subahi
2020 Computers  
Deep Learning (DL), for instance, is considered an example of a currently attractive research field that has led to advances in the areas of ML and NLP.  ...  There are various program synthesis applications built on Machine Learning (ML) and Natural Language Processing (NLP) based approaches.  ...  There is a variety of synthesis frameworks that adopt deep learning techniques, such as deep neural networks (Convolutional and Recurrent NNs) and deep reinforcement learning [116] .  ... 
doi:10.3390/computers9020027 fatcat:4t25hhuh4fcsrjzhfriggo5vra

Safe Multi-Agent Reinforcement Learning via Shielding [article]

Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers, Ufuk Topcu, Lu Feng
2021 arXiv   pre-print
Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the  ...  Therefore, we present two shielding approaches for safe MARL. In centralized shielding, we synthesize a single shield to monitor all agents' joint actions and correct any unsafe action if necessary.  ...  ACKNOWLEDGEMENTS This work was supported in part by ONR grant N00014-18-1-2829 and ARO grant W911NF-20-1-0140.  ... 
arXiv:2101.11196v2 fatcat:iwpae5q64be7pefzxmkhbf4diu
« Previous Showing results 1 — 15 out of 14,608 results