scholarly journals Fashion Style Generator

2017 ◽  
Author(s):  
Shuhui Jiang ◽  
Yun Fu
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Global Optimization ◽  
Real Time ◽  
Synthetic Image ◽  
Feed Forward Neural Network ◽  
Style Transfer ◽  
Artistic Style ◽  
The Arts ◽  
Optimization Stage

In this paper, we focus on a new problem: applying artificial intelligence to automatically generate fashion style images. Given a basic clothing image and a fashion style image (e.g., leopard print), we generate a clothing image with the certain style in real time with a neural fashion style generator. Fashion style generation is related to recent artistic style transfer works, but has its own challenges. The synthetic image should preserve the similar design as the basic clothing, and meanwhile blend the new style pattern on the clothing. Neither existing global nor patch based neural style transfer methods could well solve these challenges. In this paper, we propose an end-to-end feed-forward neural network which consists of a fashion style generator and a discriminator. The global and patch based style and content losses calculated by the discriminator alternatively back-propagate the generator network and optimize it. The global optimization stage preserves the clothing form and design and the local optimization stage preserves the detailed style pattern. Extensive experiments show that our method outperforms the state-of-the-arts.

Adaptive task scheduling in IoT using reinforcement learning

2020 ◽  
Vol 13 (3) ◽  
pp. 261-282
Author(s):  
Mohammad Khalid Pandit ◽  
Roohie Naaz Mir ◽  
Mohammad Ahsan Chishti
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Real Time ◽  
Resource Utilization ◽  
Task Scheduling ◽  
Clustering Algorithm ◽  
Fog Computing ◽  
Feed Forward Neural Network ◽  
Content Type ◽  
Communication Costs

PurposeThe intelligence in the Internet of Things (IoT) can be embedded by analyzing the huge volumes of data generated by it in an ultralow latency environment. The computational latency incurred by the cloud-only solution can be significantly brought down by the fog computing layer, which offers a computing infrastructure to minimize the latency in service delivery and execution. For this purpose, a task scheduling policy based on reinforcement learning (RL) is developed that can achieve the optimal resource utilization as well as minimum time to execute tasks and significantly reduce the communication costs during distributed execution.Design/methodology/approachTo realize this, the authors proposed a two-level neural network (NN)-based task scheduling system, where the first-level NN (feed-forward neural network/convolutional neural network [FFNN/CNN]) determines whether the data stream could be analyzed (executed) in the resource-constrained environment (edge/fog) or be directly forwarded to the cloud. The second-level NN ( RL module) schedules all the tasks sent by level 1 NN to fog layer, among the available fog devices. This real-time task assignment policy is used to minimize the total computational latency (makespan) as well as communication costs.FindingsExperimental results indicated that the RL technique works better than the computationally infeasible greedy approach for task scheduling and the combination of RL and task clustering algorithm reduces the communication costs significantly.Originality/valueThe proposed algorithm fundamentally solves the problem of task scheduling in real-time fog-based IoT with best resource utilization, minimum makespan and minimum communication cost between the tasks.

scholarly journals Real-Time Optimization and Control of Nonlinear Processes Using Machine Learning

Mathematics ◽  
2019 ◽  
Vol 7 (10) ◽  
pp. 890 ◽  
Author(s):  
Zhihao Zhang ◽  
Zhe Wu ◽  
David Rincon ◽  
Panagiotis Christofides
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Real Time ◽  
Network Model ◽  
Neural Network Model ◽  
First Principles ◽  
Chemical Process ◽  
Feed Forward Neural Network ◽  
Time Optimization ◽  
Real Time Optimization

Machine learning has attracted extensive interest in the process engineering field, due to the capability of modeling complex nonlinear process behavior. This work presents a method for combining neural network models with first-principles models in real-time optimization (RTO) and model predictive control (MPC) and demonstrates the application to two chemical process examples. First, the proposed methodology that integrates a neural network model and a first-principles model in the optimization problems of RTO and MPC is discussed. Then, two chemical process examples are presented. In the first example, a continuous stirred tank reactor (CSTR) with a reversible exothermic reaction is studied. A feed-forward neural network model is used to approximate the nonlinear reaction rate and is combined with a first-principles model in RTO and MPC. An RTO is designed to find the optimal reactor operating condition balancing energy cost and reactant conversion, and an MPC is designed to drive the process to the optimal operating condition. A variation in energy price is introduced to demonstrate that the developed RTO scheme is able to minimize operation cost and yields a closed-loop performance that is very close to the one attained by RTO/MPC using the first-principles model. In the second example, a distillation column is used to demonstrate an industrial application of the use of machine learning to model nonlinearities in RTO. A feed-forward neural network is first built to obtain the phase equilibrium properties and then combined with a first-principles model in RTO, which is designed to maximize the operation profit and calculate optimal set-points for the controllers. A variation in feed concentration is introduced to demonstrate that the developed RTO scheme can increase operation profit for all considered conditions.

Research on the Key Technologies of Intelligent Control for Cap-Shape Bending of Sheet Metal

2011 ◽  
Vol 239-242 ◽  
pp. 2867-2872
Author(s):  
Hong Lei Sun ◽  
Chun Jian Su ◽  
Rui Xue Zhai
Keyword(s):  
Neural Network ◽  
Control System ◽  
Real Time ◽  
Sheet Metal ◽  
Intelligent Control ◽  
Feed Forward Neural Network ◽  
Forming Process ◽  
Intelligent Control System ◽  
The Neural Network ◽  
Real Time Identification

The blueprint for an intelligent control system of cap-shape bending has been advanced in this paper using neural network technology, aiming at an accurate control of bending springback, the prominent problem during the forming process for the cap-shape bending of sheet metal. The feed-forward neural network of real-time identification for material performance parameters and the friction coefficient have been established. The neural network identifies the parameters for real-time needed material performance, which utilizes the measurability of the physical quantities, and predicts the parameters for optimum technology, so a satisfied accuracy of convergence has been achieved. The intelligent control experimentation system of cap-shape bending has been established, the validity of which has been tested for four kinds of materials. The result of the tests proves the feasibility of the blueprint of the intelligent control system.

scholarly journals Artistic Style Meets Artificial Intelligence

2021 ◽  
Author(s):  
Suk Kyoung Choi ◽  
Steve DiPaola ◽  
Hannu Töyrylä
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Image Processing ◽  
Lived Experience ◽  
Creative Expression ◽  
Visual Artists ◽  
Image Transformation ◽  
Artistic Style ◽  
Latent Space ◽  
Recent Developments

Recent developments in neural network image processing motivate the question, how these technologies might better serve visual artists. Research goals to date have largely focused on either pastiche interpretations of what is framed as artistic “style” or seek to divulge heretofore unimaginable dimensions of algorithmic “latent space,” but have failed to address the process an artist might actually pursue, when engaged in the reflective act of developing an image from imagination and lived experience. The tools, in other words, are constituted in research demonstrations rather than as tools of creative expression. In this article, the authors explore the phenomenology of the creative environment afforded by artificially intelligent image transformation and generation, drawn from autoethnographic reviews of the authors’ individual approaches to artificial intelligence (AI) art. They offer a post-phenomenology of “neural media” such that visual artists may begin to work with AI technologies in ways that support naturalistic processes of thinking about and interacting with computationally mediated interactive creation.

scholarly journals Analisis Pengenalan Bendera Negara Rumpun Melayu Menggunakan Metode Feed Forward Neural Network

2020 ◽  
Vol 10 (2) ◽  
pp. 144-152
Author(s):  
H Santoso ◽  
D Murdianto
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Learning Rate ◽  
Feed Forward Neural Network ◽  
Feed Forward ◽  
Brunei Darussalam ◽  
Hidden Layer

Telah dilakukan analisis pada sistem pengenalan gambar empat buah bendera negara rumpun melayu secara digital. Negara tersebut adalah Indonesia, Malaysia, Singapura, dan Brunei Darussalam. Tujuan dari penelitian ini adalah sebagai bentuk langkah awal dalam melatih sistem Artificial Intelligence (Kecerdasan Buatan) dalam membedakan empat buah negara rumpun melayu berdasarkan warna dan motif bendera pada sebuah peta digital. Proses analisis dan pelatihan pengenalan bendera tersebut menggunakan metode Feed Forward Neural Network (FFNN). Hasilnya menunjukkan bahwa penggunaan 4 buah Hidden Layer, serta penggunaan Learning Rate 0,5 memberikan kemampuan pengenalan citra bendera secara tepat dengan persentase akurasi rata-rata mencapai 74,15%.

scholarly journals Real-Time Brain-Machine Interface Achieves High-Velocity Prosthetic Finger Movements using a Biologically-Inspired Neural Network Decoder

2021 ◽  
Author(s):  
Matthew S. Willsey ◽  
Samuel R. Nason ◽  
Scott R. Ensel ◽  
Hisham Temmar ◽  
Matthew J. Mender ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Finger Movements ◽  
Feed Forward Neural Network ◽  
Current Standard ◽  
Biologically Inspired ◽  
Current State ◽  
The Neural Network ◽  
Starting Point ◽  
Prosthetic Finger

AbstractDespite the rapid progress and interest in brain-machine interfaces that restore motor function, the performance of prosthetic fingers and limbs has yet to mimic native function. The algorithm that converts brain signals to a control signal for the prosthetic device is one of the limitations in achieving rapid and realistic finger movements. To achieve more realistic finger movements, we developed a shallow feed-forward neural network, loosely inspired by the biological neural pathway, to decode real-time two-degree-of-freedom finger movements. Using a two-step training method, a recalibrated feedback intention–trained (ReFIT) neural network achieved a higher throughput with higher finger velocities and more natural appearing finger movements than the ReFIT Kalman filter, which represents the current standard. The neural network decoders introduced herein are the first to demonstrate real-time decoding of continuous movements at a level superior to the current state-of-the-art and could provide a starting point to using neural networks for the development of more naturalistic brain-controlled prostheses.

scholarly journals Artistic Style Meets Artificial Intelligence

2021 ◽  
Author(s):  
Suk Kyoung Choi ◽  
Steve DiPaola ◽  
Hannu Töyrylä
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Image Processing ◽  
Lived Experience ◽  
Creative Expression ◽  
Visual Artists ◽  
Image Transformation ◽  
Artistic Style ◽  
Latent Space ◽  
Recent Developments

Recent developments in neural network image processing motivate the question, how these technologies might better serve visual artists. Research goals to date have largely focused on either pastiche interpretations of what is framed as artistic “style” or seek to divulge heretofore unimaginable dimensions of algorithmic “latent space,” but have failed to address the process an artist might actually pursue, when engaged in the reflective act of developing an image from imagination and lived experience. The tools, in other words, are constituted in research demonstrations rather than as tools of creative expression. In this article, the authors explore the phenomenology of the creative environment afforded by artificially intelligent image transformation and generation, drawn from autoethnographic reviews of the authors’ individual approaches to artificial intelligence (AI) art. They offer a post-phenomenology of “neural media” such that visual artists may begin to work with AI technologies in ways that support naturalistic processes of thinking about and interacting with computationally mediated interactive creation.

Sign in / Sign up

Export Citation Format

Share Document