Abstract: In one embodiment, a method includes receiving a query comprising a query content object and constraints, generating a feature vector representing the query content object, accessing a sparse graph comprising nodes corresponding to candidate content objects represented by compact codes and links connecting the nodes, selecting an entry node, selecting similar content objects iteratively by identifying linked nodes of the entry node, decompressing the compact codes representing candidate content objects to generate feature vectors, selecting zero or more similar content objects based on a comparison between the feature vector representing the query content object and the feature vectors representing the candidate content objects, returning the selected similar content objects if a completion condition is satisfied, else repeating the iterative selection by using a linked node corresponding to a most similar content object as the entry node, and sending instructions for presenting one or more of the selected si

Abstract: Disclosed herein are a system, a method and a device for radioactive data generation. A defined marker can be applied or inserted within data of at least one class of a dataset having a plurality of classes of data. The defined marker data can be used to determine if a neural network model was trained using the respective class of data. A device can determine characteristics of a neural network model. The device can compare the characteristics of the neural network model with characteristics of the defined marker data incorporated into a first class of data. The device can determine, responsive to the comparing, whether the neural network model was trained using a dataset having a plurality of classes of data that includes the first class of data incorporated with the defined marker data.

Abstract: In one embodiment, a method includes receiving a query comprising a query content object and constraints, generating a feature vector representing the query content object, accessing a sparse graph comprising nodes corresponding to candidate content objects represented by compact codes and links connecting the nodes, selecting an entry node, selecting similar content objects iteratively by identifying linked nodes of the entry node, decompressing the compact codes representing candidate content objects to generate feature vectors, selecting zero or more similar content objects based on a comparison between the feature vector representing the query content object and the feature vectors representing the candidate content objects, returning the selected similar content objects if a completion condition is satisfied, else repeating the iterative selection by using a linked node corresponding to a most similar content object as the entry node, and sending instructions for presenting one or more of the selected si

Abstract: In one embodiment, a method includes receiving a query, wherein the query is represented by an n-dimensional vector in an n-dimensional vector space; quantizing the vector representing the query using a quantizer, wherein the quantized vector corresponds to a polysemous code, and wherein the quantizer has been trained by machine learning to determine polysemous codes such that the Hamming distance approximates the inter-centroid distance using an objective function; calculating, for each of a plurality of content objects, a Hamming distance between the polysemous code corresponding to the vector representing the query and a polysemous code corresponding to a quantized vector representing the content object; and determining that a content object of the plurality of content objects is an approximate nearest neighbor to the query based on determining that the calculated Hamming distance is less than a threshold amount.

Abstract: The present disclosure relates to an assistance device for image recognition that comprises a memory storing sets of image descriptors, respectively associated with an image area and including first vector data, second angle data, and third scale data. A first operator receives a designation of two descriptors and establishes a Boolean representing a check of a similarity criterion of the descriptor vectors from a comparison among first data. A second operator receives a designation of two descriptors and establishes a rotation angle parameter from the second data. A third operator receives a designation of two descriptors and establishes a scale factor parameter from the third data.

Abstract: The present disclosure relates to an assistance device for image recognition that comprises a memory storing sets of image descriptors, respectively associated with an image area and including first vector data, second angle data, and third scale data. A first operator receives a designation of two descriptors and establishes a Boolean representing a check of a similarity criterion of the descriptor vectors from a comparison among first data. A second operator receives a designation of two descriptors and establishes a rotation angle parameter from the second data. A third operator receives a designation of two descriptors and establishes a scale factor parameter from the third data.

Abstract: The invention concerns a digital data compression encoder, characterized in that it comprises: an input for a first data flow (SH), and a second data flow (SL), an encoding module, matching symbols of the first data flow, and code words, wherein, for certain symbols, there exist several words, called redundant, corresponding to the same symbol, and a processing module for encoding the symbols of the first data flow based on the correspondence, by selecting among the redundant words, on the basis of at least part of the second data flow.

Abstract: The invention concerns a digital data compression encoder, characterized in that it comprises: an input for a first data flow (SH), and a second data flow (SL), an encoding module, matching symbols of the first data flow, and code words, wherein, for certain symbols, there exist several words, called redundant, corresponding to the same symbol, and a processing module for encoding the symbols of the first data flow based on the correspondence, by selecting among the redundant words, on the basis of at least part of the second data flow.