Abstract: A system is configured to provide access to a machine learning model by using a hybrid configuration comprising a dedicate server on which an instance of a model server is installed, and a serverless compute architecture that interfaces with an instance of the model server using an extension. A first portion of requests directed to the model server are processed by the dedicated server, and a second portion of the requests is processed by the serverless compute architecture.

Abstract: Techniques for caching in a machine learning model (ML) hosting service are described. ML model usage data is aggregated from host usage data provided from each host of a first set of hosts, the ML model usage data including, for a particular ML model, a number of inference requests to the particular ML model. A priority order of hosts in a second set of hosts to service an inference request for the particular ML model is calculated. Based on the ML model usage data and the priority order, a set of ML models to load to a particular host in the second set of hosts is determined. The particular host is caused to load the set of ML models. A router is updated to direct ML model inference requests amongst the second set of hosts.

Abstract: A serverless computing system is configured to provide access to a machine learning model by at least associating an endpoint, comprising code that accesses the machine learning model, with an extension that interfaces between a serverless compute architecture and the endpoint. A request to perform an inference is received by the system and processed by using the serverless compute architecture to execute a compute function. The compute function cases the extension to interface with the endpoint to cause the machine learning model to perform the inference.

Abstract: Systems and method are disclosed for processing unrecognized user queries. A received user query is classified via a first machine learning model. A first classification determination is made for the user query. In response to the first classification determination, features of the user query are identified via a second machine learning model. The user query is grouped into a cluster based on the features of the user query. Information about the cluster is displayed for prompting a user action. The user action may include identification of an intent for the user query.

Abstract: A serverless computing system is configured to provide access to a machine learning model by at least associating an endpoint, comprising code that accesses the machine learning model, with an extension that interfaces between a serverless compute architecture and the endpoint. A request to perform an inference is received by the system and processed by using the serverless compute architecture to execute a compute function. The compute function cases the extension to interface with the endpoint to cause the machine learning model to perform the inference.

Abstract: A system is configured to provide access to a machine learning model by using a hybrid configuration comprising a dedicate server on which an instance of a model server is installed, and a serverless compute architecture that interfaces with an instance of the model server using an extension. A first portion of requests directed to the model server are processed by the dedicated server, and a second portion of the requests is processed by the serverless compute architecture.

Abstract: EZ Hi-Def. device is comprised of 6 round bars arranged in a hexagon and a base ring. Round bar handles are located outside of base ring to make the shape of hexagon smaller or bigger, so that bars don't block the live view of the camera or don't show in a photograph. Six round bars reflect light to the camera lens to provide two critical factors to capture a high definition photograph: more image data and increased light sensitivity of the camera.

Abstract: The present invention provides a device, EZ Hi-Def., which can be mounted to a digital camera lens to take a high-definition photo. Photograph is from light, and it cannot be emphasized enough that without light there is no photograph. This simplicity and low cost device can turn photography into new chapter from digital to high definition.

Abstract: A device to create high definition photos includes: a lens for receiving light and transmitting an image; and a plurality of parallel blocking rods to delay the light within the lens; wherein the lens receives the light, the rods delay the light, and the lens transmits the delayed light, thereby providing an enhanced image of the item.

Abstract: An apparatus and method of communicating between devices coupled to two networks. The first network comprises a terminal, containing an Ethernet interface, communication medium and an Ethernet interface contained in a concentrator. The second network comprises an Asynchronous Transfer Mode (ATM) interface contained in a switch, a communication medium and other components of an ATM network. Terminals transmit packets to other devices by: transmitting a packet to the concentrator, the concentrator segments the packet's information into ATM cells, and transmits the cells over the ATM network. The Terminals receive packets from other devices by: the ATM network transmitting cells to a concentrator, the cells being reassembled into Ethernet packets, then the packets being transmitted to the appropriate terminal.