Challenges and opportunities for optical neural network (Conference Presentation)

2020 ◽  
Author(s):  
Arka Majumdar
Keyword(s):  
Neural Network ◽  
Challenges And Opportunities ◽  
Optical Neural Network

scholarly journals Freely scalable and reconfigurable optical hardware for deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Liane Bernstein ◽  
Alexander Sludds ◽  
Ryan Hamerly ◽  
Vivienne Sze ◽  
Joel Emer ◽  
...  
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Data Transfer ◽  
Power Delivery ◽  
Optical Data ◽  
Optical Multicast ◽  
Optical Neural Network ◽  
Fully Connected ◽  
Management Power

AbstractAs deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are impeded by the costs of communication, thermal management, power delivery and clocking. To improve scalability, we propose a digital optical neural network (DONN) with intralayer optical interconnects and reconfigurable input values. The path-length-independence of optical energy consumption enables information locality between a transmitter and a large number of arbitrarily arranged receivers, which allows greater flexibility in architecture design to circumvent scaling limitations. In a proof-of-concept experiment, we demonstrate optical multicast in the classification of 500 MNIST images with a 3-layer, fully-connected network. We also analyze the energy consumption of the DONN and find that digital optical data transfer is beneficial over electronics when the spacing of computational units is on the order of $$>10\,\upmu $$ > 10 μ m.

scholarly journals Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

2021 ◽  
Vol 11 (7) ◽  
pp. 3059
Author(s):  
Myeong-Hun Jeong ◽  
Tae-Young Lee ◽  
Seung-Bae Jeon ◽  
Minkyo Youm
Keyword(s):  
Neural Network ◽  
Intelligent Transportation Systems ◽  
Moving Average ◽  
Computational Cost ◽  
Nonlinear Problems ◽  
Transportation Systems ◽  
Mobility Data ◽  
Challenges And Opportunities ◽  
Moving Average Model ◽  
Gated Recurrent Unit

Movement analytics and mobility insights play a crucial role in urban planning and transportation management. The plethora of mobility data sources, such as GPS trajectories, poses new challenges and opportunities for understanding and predicting movement patterns. In this study, we predict highway speed using a gated recurrent unit (GRU) neural network. Based on statistical models, previous approaches suffer from the inherited features of traffic data, such as nonlinear problems. The proposed method predicts highway speed based on the GRU method after training on digital tachograph data (DTG). The DTG data were recorded in one month, giving approximately 300 million records. These data included the velocity and locations of vehicles on the highway. Experimental results demonstrate that the GRU-based deep learning approach outperformed the state-of-the-art alternatives, the autoregressive integrated moving average model, and the long short-term neural network (LSTM) model, in terms of prediction accuracy. Further, the computational cost of the GRU model was lower than that of the LSTM. The proposed method can be applied to traffic prediction and intelligent transportation systems.

Piecewise quadratic optical neural network

1993 ◽  
Author(s):  
Sanjay S. Natarajan ◽  
David P. Casasent
Keyword(s):  
Neural Network ◽  
Optical Neural Network

scholarly journals Brain Musics: History, Precedents, and Commentary on Whalley, Mavros and Furniss

2015 ◽  
Vol 9 (3-4) ◽  
pp. 277 ◽  
Author(s):  
Miguel Ortiz ◽  
Mick Grierson ◽  
Atau Tanaka
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Musical Performance ◽  
Eeg Signals ◽  
Live Electronics ◽  
Broad Area ◽  
Direct Mapping ◽  
Challenges And Opportunities ◽  
History Of ◽  
Small Ensemble

<p>Whalley, Mavros and Furniss (this issue) explore questions of agency, control and interaction, as well as the embodied nature of musical performance in relation to the use of human-computer interaction through the work <em>Clasp Together (beta) </em>for small ensemble and live electronics. The underlying concept of the piece focuses on direct mapping of a human neural network (embodied by a performer within the ensemble) to an artificial neural network running on a computer. With our commentary, we contextualize the work by offering a brief history of music that uses brainwaves. We review the use of EEG signals for musical performance and point at precedents in EEG-based musical practice. We hope to more clearly situate <em>Clasp Together (beta)</em> in the broad area of Brain Computer Musical Interfaces and discuss the challenges and opportunities that these technologies offer for composers.</p>

Sign in / Sign up

Export Citation Format

Share Document