Phys.org August 21, 2024 Existing optical switching solutions are inadequate for addressing flexible information exchange among the mode channels. Researchers in China introduced a flexible mode switching system in a multimode fibre based on an optical neural network chip. The system utilized the flexibility of on-chip optical neural networks along with an all-fibre orbital angular momentum (OAM) mode multiplexer-demultiplexer to achieve mode switching among the three OAM modes within a multimode fibre. They validated the system by successfully transmitting different modulation formats across various modes. According to the researchers their system could provide effective optical switching in practical multimode communication […]
Tag Archives: neural network
“Liquid” machine-learning system adapts to changing conditions
MIT News January 28, 2021 An international team of researchers (USA – MIT, Austria) designed a neural network that can adapt to the variability of real-world systems. They took inspiration from C.elegans which has only 302 neurons in its nervous system, yet it can generate unexpectedly complex dynamics. The equations they used to structure their neural network allowed the parameters to change over time based on the results of a nested set of differential equations. Most neural networks’ behavior is fixed after the training phase. The fluidity of their “liquid” network makes it more resilient to unexpected or noisy data and […]
New optical system could lead to devices that can recognize objects instantly
Technology.org March 5, 2020 Diffractive optical network is a recently introduced optical computing framework that merges wave optics with deep-learning methods to design optical neural networks. Previous diffractive approaches employed monochromatic coherent light as the illumination source. Researchers at UCLA designed a broadband diffractive optical neural network that simultaneously processes a continuum of wavelengths generated by a temporally incoherent broadband source to all-optically perform a specific task learned using deep learning. They fabricated and tested seven different multi-layer, diffractive optical systems that transform the optical wavefront generated by a broadband THz pulse to realize a series of tunable, single-passband and […]
Deep-learning technique reveals ‘invisible’ objects in the dark
Science Daily December 12, 2018 Using deep neural network technique researchers at MIT reconstructed transparent objects from images of those objects, taken in almost pitch-black conditions. A computer was trained to recognize more than 10,000 transparent glass-like etchings, based on extremely grainy images of those patterns, with about one photon per pixel. They found that the computer learned to reconstruct the transparent object from the new grainy image, not included in the training data. The technique is of practical importance for medical imaging to lower the exposure of the patient to harmful radiation, and for astronomical imaging…read more. TECHNICAL ARTICLE
The ultimate combination: A 3D-printed optical deep learning network
Eurekalert July 26, 2018 Researchers at UCLA have developed an optical deep learning framework called Diffractive Deep Neural Network (D2NN), that consists of layers of 3-D-printed, optically diffractive surfaces that work together to process information. Each point on a given layer either transmits or reflects an incoming wave, which represents an artificial neuron that is connected to other neurons of the following layers through optical diffraction. By altering the phase and amplitude, each “neuron” is tunable. They demonstrated that after training the system on the handwritten digits, D2NN could recognise the numbers with 95.08% accuracy. According to the researchers the […]
Optical neural network demo
Science Daily July 28, 2018 Researchers at NIST stacked waveguides made of silicon nitride to form a three-dimensional grid with 10 inputs or “upstream” neurons each connecting to 10 outputs or “downstream” neurons, for a total of 100 receivers. They created software to automatically generate signal routing, with adjustable levels of connectivity between the neurons. Laser light was directed into the chip through an optical fiber routing each input to every output group, following a selected distribution pattern for light intensity or power. To evaluate the results, researchers made images of the output signals. The output was highly uniform, with […]
Researchers move closer to completely optical artificial neural network
Eurekalert July 19, 2018 There is interest in using integrated optics as a hardware platform for implementing artificial neural networks. However, currently on the integrated photonics platform there is no efficient protocol for the training of these networks. Researchers at Stanford University have developed a method that enables highly efficient, in situ training of a photonic neural network by using adjoint variable methods to derive the photonic analogue of the backpropagation algorithm. As demonstration they trained a numerically simulated photonic artificial neural network. The method may be of broad interest to experimental sensitivity analysis of photonic systems and optimization of […]
Scientists Have Invented a Software That Can ‘See’ Several Minutes Into The Future
Science Alert June 14, 2018 Researchers in Germany wanted to see if a program could list a sequence of actions up to five minutes into the future based on watching the first few steps of an activity. They trained software to guess what a chef would do next by showing it a number of videos of people making breakfast or a salad. They then showed the program a completely new video of another person preparing a similar meal, and watched how it guessed upcoming steps and their respective duration. One approach anticipated future actions and reflected before anticipating again, and […]
New algorithm can create movies from just a few snippets of text
Science Magazine February 23, 2018 Researchers in Belgium have developed a machine learning a neural network algorithm. During training, software assesses its performance after each attempt, and feedback circulates through the millions of network connections to refine future computations. The first stage uses the text to create a “gist” of the video, the second stage takes both the gist and the text and produces a short video. During training, a second network acts as a “discriminator.” As it gets better, it becomes a harsher critic, and its feedback sets a higher bar for the generator network. Currently, the videos are […]
Why even a moth’s brain is smarter than an AI
MIT Technology Review February 19, 2018 Some critical machine-learning mechanisms have no analogue in the natural world, where learning seems to occur in a different way. Researchers at the University of Washington have created an artificial neural network that mimics the structure and behavior of the olfactory learning system in Manduca sexta moths. Their model can robustly learn new odors, and their simulations of integrate-and-fire neurons match the statistical features of in vivo firing rate data. This work that could have significant implications for the design of synthetic neural networks that need to learn quickly…read more. Open Access TECHNICAL ARTICLE