Deep neural networks (DNNs) are used to classify and reconstruct the input images from the intensity of the speckle patterns that result after the inputs are propagated through multimode fiber (MMF). We were able to demonstrate this result for fibers up to 1 km long by training the DNNs with a database of 16,000 handwritten digits. Better recognition accuracy was obtained when the DNNs were trained to first reconstruct the input and then classify based on the recovered image. We observed remarkable robustness against environmental instabilities and tolerance to deviations of the input pattern from the patterns with which the DNN was originally trained.

Learning to see through multimode fibers

The recent advances of polymer technology allowed the introduction of plastic optical fiber in sensor design. The advantages of optical metrology with plastic optical fiber have attracted the attention of the scientific community, as they allow the development of low-cost or cost competitive systems compared with conventional technologies. In this paper, the current state of the art of plastic optical fiber technology will be reviewed, namely its main characteristics and sensing advantages. Several measurement techniques will be described, with a strong focus on interrogation approaches based on intensity variation in transmission and reflection. The potential applications involving structural health monitoring, medicine, environment and the biological and chemical area are also presented.

Optical sensors based on plastic fibers.

This tutorial clarifies the axiomatic definition of (v(α); i(β)) circuit elements via a lookup table dubbed an A-pad, of admissible (v; i) signals measured via Gedanken probing circuits. The (v(α); i(β)) elements are ordered via a complexity metric. Under this metric, the memristor emerges naturally as the fourth element, characterized by a state-dependent Ohm's law. A logical generalization to memristive devices reveals a common fingerprint consisting of a dense continuum of pinched hysteresis loops whose area decreases with the frequency ω and tends to a straight line as ω ~ ∞, for all bipolar periodic signals and for all initial conditions. This common fingerprint suggests that the term memristor be used hence-forth as a moniker for memristive devices.

The Fourth Element.

http://www.bits-pilani.ac.in/uploads/Hyderabad/hota/kamal-sarath-hota.pdf

Big Data Analytics framework for Peer-to-Peer Botnet detection using Random Forests

Multimode fibers (MMFs) are an example of a highly scattering medium, which scramble the coherent light propagating within them to produce seemingly random patterns. Thus, for applications such as imaging and image projection through an MMF, careful measurements of the relationship between the inputs and outputs of the fiber are required. We show, as a proof of concept, that a deep neural network can learn the input-output relationship in a 0.75 m long MMF. Specifically, we demonstrate that a deep convolutional neural network (CNN) can learn the nonlinear relationships between the amplitude of the speckle pattern (phase information lost) obtained at the output of the fiber and the phase or the amplitude at the input of the fiber. Effectively, the network performs a nonlinear inversion task. We obtained image fidelities (correlations) as high as ~98% for reconstruction and ~94% for image projection in the MMF compared with the image recovered using the full knowledge of the system transmission characterized with the complex measured matrix. We further show that the network can be trained for transfer learning, i.e., it can transmit images through the MMF, which belongs to another class not used for training/testing. A convolutional neural network (CNN) can successfully learn the nonlinear transmission characteristics of a multimode fibre thus allowing accurate image transmission and reconstruction. Propagation along a multimode fibre usually scrambles an input image, resulting in a seemingly random speckle pattern at the output. Babak Rahmani and coworkers from the Ecole Polytechnique Federale de Lausanne in Switzerland have now shown that a deep neural network(either a 22-layer CNN based on VGG-net technology or a 20-layer CNN based on Res-net technology) can learn the input-output relationship in a 0.75 m long piece of multimode fibre) and thus undo this scrambling. Experiments showed that both neural networks could perform highly accurate image reconstruction with an image fidelity as high as ~98% for image reconstruction and ~94% for image projection in the best case.

/pdf/multimode-optical-fiber-transmission-with-a-deep-learning-4qx1t0g7zn.pdf

Multimode optical fiber transmission with a deep learning network.

A neural network approach to robust shape classification

Model-based intrusion detection and knowledge discovery are combined to cluster and classify P2P botnet traffic and other malignant network activity by using a Self-Organizing Map (SOM) self-trained on denied Internet firewall log entries. The SOM analyzed new firewall log entries in a case study to classify similar network activity, and discovered previously unknown local P2P bot traffic and other security issues.

/pdf/a-self-organizing-map-and-its-modeling-for-discovering-df3mfhhrej.pdf

A self-organizing map and its modeling for discovering malignant network traffic

A new technique for transmitting information through multimode fiber-optic cables is presented. This technique sends parallel channels through the fiber-optic cable, thereby greatly improving the data transmission rate compared with that of the current technology, which uses serial data transmission through single-mode fiber. An artificial neural network is employed to decipher the transmitted information from the received speckle pattern. Several different preprocessing algorithms are developed, tested, and evaluated. These algorithms employ average region intensity, distributed individual pixel intensity, and maximum mean-square-difference optimal group selection methods. The effect of modal dispersion on the data rate is analyzed. An increased data transmission rate by a factor of 37 over that of single-mode fibers is realized. When implementing our technique, we can increase the channel capacity of a typical multimode fiber by a factor of 6.

Neural network-based multimode fiber-optic information transmission

This paper describes a novel A/D converter called "Binary Delta-Sigma Modulator" (BDSM) which operates only with nonnegative signal with positive feedback and binary threshold. This important modification to the conventional delta-sigma modulator makes the high-speed (>100GHz) all-optical implementation possible. It has also the capability to modify its own sampling frequency as well as its input dynamic range. This adaptive feature helps designers to optimize the system performance under highly noisy environment and also manage the power consumption of the A/D converters.

Mohammad R. Sayeh

Papers

A neural network approach to robust shape classification

A self-organizing map and its modeling for discovering malignant network traffic

Neural network-based multimode fiber-optic information transmission

All optical binary delta-sigma modulator

On linearity of all optical asynchronous binary delta–sigma modulator