A neural network processing system having multiple layers is provided. Each layer includes a bidirectional Synaptic Network Channel (SNC) for concurrently transmitting weighted sums, y.sub.F(t)'s and x.sub.B(t)'s, as an elastic wave superposition of inputs, x.sub.F(t)'s and y.sub.B(t)'s, respectively. Each input is multiplied and added with corresponding weights w's encoded in variable splitters and combiners in forward and backward directions, respectively. Each layer includes unidirectional Signal Reshaping (SR) units, I's and L's for inference and learning, respectively, by generating inputs for a following layer in forward and backward directions from a current layer's weighted sums y.sub.F(t)'s and x.sub.B(t)'s, respectively. Each layer includes a Hybrid Coupler (HC) to connect the bidirectional SNC and the unidirectional SR units. Each layer includes a weight update unit to calculate each weight difference using an input y.sub.Bi(t) or a weighted sum y.sub.Fi(t) and an input x.sub.Fj(t) to update a weight w.sub.ij for a current layer.

A neural network processing system having multiple layers is provided. Each layer includes a bidirectional Synaptic Network Channel (SNC) for concurrently transmitting weighted sums, y.sub.F(t)'s and x.sub.B(t)'s, as an elastic wave superposition of inputs, x.sub.F(t)'s and y.sub.B(t)'s, respectively. Each input is multiplied and added with corresponding weights w's encoded in variable splitters and combiners in forward and backward directions, respectively. Each layer includes unidirectional Signal Reshaping (SR) units, I's and L's for inference and learning, respectively, by generating inputs for a following layer in forward and backward directions from a current layer's weighted sums y.sub.F(t)'s and x.sub.B(t)'s, respectively. Each layer includes a Hybrid Coupler (HC) to connect the bidirectional SNC and the unidirectional SR units. Each layer includes a weight update unit to calculate each weight difference using an input y.sub.Bi(t) or a weighted sum y.sub.Fi(t) and an input x.sub.Fj(t) to update a weight w.sub.ij for a current layer.

The automatic classification of network devices in a network. Specifically, the disclosure entails the designation of network device roles to network devices, as well as the clustering of network devices into logical groups. The association of network devices with network device roles and logical groups may be contingent on the connections between the network devices and a set of network device classification heuristics.

In a method of preventing fraudulent online financial transactions, a request to authorize an online, financial transaction may be received, where the transaction is associated with a debit or credit card account. A computing device at which information associated with the debit or credit card account was entered for the transaction may be identified, and a first geographic location at which the computing device resides may be determined. Based upon geolocation data indicating one or more geographic locations of the authorized cardholder, it may be determined that the authorized cardholder was at a second geographic location at a time of the transaction. If the second geographic location does not correspond to the first geographic location, the financial transaction may be prevented from being executed.

A virtual file organization system, method and program product are disclosed. Included is a system that assigns classification tags to files stored within a storage system based on a natural language processing (NLP) context analysis of each file; and a virtual smart folder that is viewable within a user interface, wherein: opening the virtual smart folder causes a set of virtual subfolders to be displayed in which each virtual subfolder includes a category title; opening of a virtual subfolder causes a set of files residing at disparate locations in the storage system to be displayed; and the files displayed by opening the virtual subfolder each include an assigned classification tag that is associated with the category title of the virtual subfolder.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learning estimation networks in a communications system. One of the methods includes: processing first information with ground truth information to generate a first RF signal by altering the first information by channel impairment having at least one channel effect, using a receiver to process the first RF signal to generate second information, training a machine-learning estimation network based on a network architecture, the second information, and the ground truth information, receiving by the receiver a second RF signal transmitted through a communication channel including the at least one channel effect, inferring by the trained estimation network the receiver to estimate an offset of the second RF signal caused by the at least one channel effect, and correcting the offset of the RF signal with the estimated offset to obtain a recovered RF signal.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learning estimation networks in a communications system. One of the methods includes: processing first information with ground truth information to generate a first RF signal by altering the first information by channel impairment having at least one channel effect, using a receiver to process the first RF signal to generate second information, training a machine-learning estimation network based on a network architecture, the second information, and the ground truth information, receiving by the receiver a second RF signal transmitted through a communication channel including the at least one channel effect, inferring by the trained estimation network the receiver to estimate an offset of the second RF signal caused by the at least one channel effect, and correcting the offset of the RF signal with the estimated offset to obtain a recovered RF signal.

An authentication model dynamically adjusts authentication factors required for access to a remote resource based on changes to a risk score for a user, a device, or some combination of these. For example, the authentication model may conditionally specify the number and type of authentication factors required by a user/device pair, and may dynamically alter authentication requirements based on changes to a current risk assessment for the user/device while the remote resource is in use.

An artificial intelligence based method and apparatus for processing information. A specific embodiment of the method includes: acquiring search click information recorded within a predetermined time period; generating a candidate entry set by selecting, from the search click information, entries having click volumes exceeding a click volume threshold within a preset unit time period; forming, for each candidate entry in the candidate entry set, a click volume sequence according to a chronological order of each of the click volumes corresponding to the candidate entry in the predetermined time period; determining, based on click volume sequences, categories of the candidate entries respectively corresponding to click volume sequences; and determining candidate entries having the categories being a preset category as points of interest to generate a set of points of interest.

Methods and systems are disclosed using camera devices for deep channel and Convolutional Neural Network (CNN) images and formats. In one example, image values are captured by a color sensor array in an image capturing device or camera. The image values provide color channel data. The captured image values by the color sensor array are input to a CNN having at least one CNN layer. The CNN provides CNN channel data for each layer. The color channel data and CNN channel data is to form a deep channel image that stored in a memory. In another example, image values are captured by sensor array. The captured image values by the sensor array are input a CNN having a first CNN layer. An output is generated at the first CNN layer using the captured image values by the color sensor array. The output of the first CNN layer is stored as a feature map of the captured image.