The ELM system builds on basic principles, including avoiding complex training methods such as backpropagation. It bridges the concepts of reservoir computing and optical neural networks using nonlinear propagation in fibers as a computational medium. The team aims to extend previous proof-of-concept optical ELMs by providing a quantitative framework based on dimensionality via principal components analysis and consistency metrics.<\/p>\n
Three-step process<\/p>\n
The entire process of executing the team\u2019s approach can be divided into three steps:<\/p>\n
First, information is encoded by modulating the spectral phase of femtosecond laser pulses using a spatial light modulator. Optical fiber is used to confine light to a smaller area. With an encoded relative delay consistent with an image, the team found that the subsequent spectrum that\u2019s transformed by the nonlinear interaction of light and glass has enough information to classify catalog handwritten digits. The researchers liken it to the conventional Modified National Institute of Standards and Technology (MNIST) database, a large collection of handwritten digits commonly used for training image processing systems.<\/p>\n
Next, these modulated pulses propagate through the nonlinear fiber, where nonlinearity and dispersion induce spectral broadening. Hary says this \u201cacts as a nonlinear transformation of the information.\u201d And lastly, the output spectrum is collected with an optical spectrum analyzer; the linear readout operation is computed offline.<\/p>\n
\u201cThere is a growing demand for analog optical processors that can perform real-time signal classification and metrology with minimal latency and power,\u201d Hary says.<\/p>\n
Notable findings<\/p>\n
In their work, the researchers discovered performance and nonlinearity are not monotonically related. \u201cMore input power does not always mean better performance,\u201d Hary says. \u201cThe system reaches its best classification accuracy of up to 87% at moderate power.\u201d<\/p>\n
She says the team\u2019s best results were achieved when the MNIST images were heavily compressed down to 20 to 40 components, rather than using the 784 they started with. This suggests their ELM system acts as a powerful feature expander.<\/p>\n
The researchers also discovered the dynamics useful for computing are confined within 40 nm around the pump, but also that nonlinear broadening can spread light over hundreds of nanometers.<\/p>\n
\u201cIn my opinion, the most interesting finding is the introduction of a new methodology for benchmarking optical neural networks,\u201d Hary says.<\/p>\n","protected":false},"excerpt":{"rendered":"The ELM system builds on basic principles, including avoiding complex training methods such as backpropagation. It bridges the…\n","protected":false},"author":3,"featured_media":155073,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22],"tags":[745,158,67,132,68],"class_list":{"0":"post-155072","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-computing","8":"tag-computing","9":"tag-technology","10":"tag-united-states","11":"tag-unitedstates","12":"tag-us"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@us\/115048419574947993","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/posts\/155072","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/comments?post=155072"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/posts\/155072\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/media\/155073"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/media?parent=155072"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/categories?post=155072"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/us\/wp-json\/wp\/v2\/tags?post=155072"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}