Constrained Image Generation Using Binarized Neural Networks with Decision Procedures

نویسندگان

  • Svyatoslav Korneev
  • Nina Narodytska
  • Luca Pulina
  • Armando Tacchella
  • Nikolaj Bjørner
  • Shmuel Sagiv
چکیده

We consider the problem of binary image generation with given properties. This problem arises in a number of practical applications, including generation of artificial porous medium for an electrode of lithium-ion batteries, for composed materials, etc. A generated image represents a porous medium and, as such, it is subject to two sets of constraints: topological constraints on the structure and process constraints on the physical process over this structure. To perform image generation we need to define a mapping from a porous medium to its physical process parameters. For a given geometry of a porous medium, this mapping can be done by solving a partial differential equation (PDE). However, embedding a PDE solver into the search procedure is computationally expensive. We use a binarized neural network to approximate a PDE solver. This allows us to encode the entire problem as a logical formula. Our main contribution is that, for the first time, we show that this problem can be tackled using decision procedures. Our experiments show that our model is able to produce random constrained images that satisfy both topological and process constraints.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Diagnosis of brain tumor using image processing and determination of its type with RVM neural networks

Typically, the diagnosis of a tumor is done through surgical sampling, which is more precise with existing methods. The difference is that this is an aggressive, time consuming and expensive way. In the statistical method, due to the complexity of the brain tissues and the similarity between the cancerous cells and the natural tissues, even a radiologist or an expert physician may also be in er...

متن کامل

Static Security Constrained Generation Scheduling Using Sensitivity Characteristics of Neural Network

This paper proposes a novel approach for generation scheduling using sensitivitycharacteristic of a Security Analyzer Neural Network (SANN) for improving static securityof power system. In this paper, the potential overloading at the post contingency steadystateassociated with each line outage is proposed as a security index which is used forevaluation and enhancement of system static security....

متن کامل

Verifying Properties of Binarized Deep Neural Networks

Understanding properties of deep neural networks is an important challenge in deep learning. In this paper, we take a step in this direction by proposing a rigorous way of verifying properties of a popular class of neural networks, Binarized Neural Networks, using the well-developed means of Boolean satisfiability. Our main contribution is a construction that creates a representation of a binar...

متن کامل

Binarized Neural Networks

In this work we introduce a binarized deep neural network (BDNN) model. BDNNs are trained using a novel binarized back propagation algorithm (BBP), which uses binary weights and binary neurons during the forward and backward propagation, while retaining precision of the stored weights in which gradients are accumulated. At test phase, BDNNs are fully binarized and can be implemented in hardware...

متن کامل

Robust Fault Detection on Boiler-turbine Unit Actuators Using Dynamic Neural Networks

Due to the important role of the boiler-turbine units in industries and electricity generation, it is important to diagnose different types of faults in different parts of boiler-turbine system. Different parts of a boiler-turbine system like the sensor or actuator or plant can be affected by various types of faults. In this paper, the effects of the occurrence of faults on the actuators are in...

متن کامل

ذخیره 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 نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1802.08795  شماره 

صفحات  -

تاریخ انتشار 2018