Abstract: The present invention discloses an intelligent control system and method for a doll clothing cooling device, the system including an information acquisition system, an image acquisition system, a computer vision system, and a central control system. The information acquisition system acquires environmental parameters and human physiological parameters in the mannequin garment. The image acquisition system acquires a video image of a human face and transmits it to the computer vision system to calculate a human head temperature. The central control system predicts the human thermal sensation data based on the acquired environmental and physiological parameters. The opening degree of the cooling device of the mannequin garment is automatically adjusted according to the human body heat sensation data and the voice instructions of the wearer of the mannequin garment. The invention solves the problem of dynamically improving the thermal comfort of the wearer of the mannequin costume in real time.

Abstract: The disclosure is directed towards automatically tuning quantization-based approximate nearest neighbors (ANN) search methods and systems (e.g., search engines) to perform at the speed-recall pareto frontier. With a desired search cost or recall as input, the embodiments employ Lagrangian-based methods to perform constrained optimization on theoretically-grounded search cost and recall models. The resulting tunings, when paired with the efficient quantization-based ANN implementation of the embodiments, exhibit excellent performance on standard benchmarks while requiring minimal tuning or configuration complexity.

Abstract: Generally, the present disclosure is directed to systems and methods of quantizing a database with respect to a novel loss or quantization error function which applies a weight to an error measurement of quantized elements respectively corresponding to the datapoints in the database. The weight is determined based on the magnitude of an inner product between the respective datapoints and a query compared therewith. In contrast to previous work, embodiments of the proposed loss function are responsive to the expected magnitude of an inner product between the respective datapoints and a query compared therewith and can prioritize error reduction for higher-ranked pairings of the query and the datapoints. Thus, the systems and methods of the present disclosure provide solutions to some of the problems with traditional quantization approaches, which regard all error as equally impactful.

Abstract: Provided is a scalable and cost-efficient storage architecture for large-scale datasets, such as Internet-scale datasets that include very large numbers (e.g., billions) of data elements. More particularly, provided is a bifurcated storage architecture that includes a first data index stored by a first set of storage media and a second data index stored by a second set of storage media, where the first set of storage media has a lower latency than the second set of storage media.

Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a multiscale quantization model that is configured to provide a quantized dataset. In particular, the multiscale quantization model can receive and perform vector quantization of a first dataset. The multiscale quantization model can generate a residual dataset based at least in part on a result of the vector quantization. The multiscale quantization model can apply a rotation matrix to the residual dataset to generate a rotated residual dataset that includes a plurality of rotated residuals. The multiscale quantization model can perform reparameterization of each rotated residual in the rotated residual dataset into a direction component and a scale component. The multiscale quantization model can perform product quantization of the direction components of the plurality of rotated residuals, and perform scalar quantization of the scale components of the plurality of rotated residuals.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a kNN computation using a hardware accelerator. One of the methods includes obtaining a set of one or more query vectors; obtaining a set of database vectors; and performing, on a hardware accelerator and for each query vector in the set, a search for the k most similar database vectors to the query vector, comprising: computing, by circuitry of the hardware accelerator and for each query vector, a respective similarity value between the query vector and each database vector; and for each query vector, identifying, by the hardware accelerator and for each bin, (i) an index of the most similar database vector within the bin and (ii) the respective similarity value for the most similar database vector within the bin.

Abstract: The invention discloses a spray cooling fan control system and method based on computer vision technology. The data acquisition system monitors person thermal comfort through various non-contact measurement methods, which improves the accuracy and instantaneity and achieves human thermal comfort and energy saving. The information processing system adjusts the air and spray volume based on human skin temperature and thermal sensation and plans the mobile path. The mobile control system moves the spray cooling fan to the optimal location so that the mobility and flexibility are enhanced. The intelligent voice interaction system and the end control system control the opening of the fan intelligently and humanely so that people become the main subject which controls the environmental temperature optimization equipment. Consequently, the invention cools person precisely and meets the thermal environment control and personnel thermal needs quickly.

Abstract: Generally, the present disclosure is directed to systems and methods of quantizing a database with respect to a novel loss or quantization error function which applies a weight to an error measurement of quantized elements respectively corresponding to the datapoints in the database. The weight is determined based on the magnitude of an inner product between the respective datapoints and a query compared therewith. In contrast to previous work, embodiments of the proposed loss function are responsive to the expected magnitude of an inner product between the respective datapoints and a query compared therewith and can prioritize error reduction for higher-ranked pairings of the query and the datapoints. Thus, the systems and methods of the present disclosure provide solutions to some of the problems with traditional quantization approaches, which regard all error as equally impactful.

Abstract: Provided are systems and methods which more efficiency train embedding models through the use of a cache of item embeddings for candidate items over a number of training iterations. The cached item embeddings can be “stale” embeddings that were generated by a previous version of the model at a previous training iteration. Specifically, at each iteration, the (potentially stale) item embeddings included in the cache can be used when generating similarity scores that are the basis for sampling a number of items to use as negatives in the current training iteration. For example, a Gumbel-Max sampling approach can be used to sample negative items that will enable an approximation of a true gradient. New embeddings can be generated for the sampled negative items and can be used to train the model at the current iteration.

Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a multiscale quantization model that is configured to provide a quantized dataset. In particular, the multiscale quantization model can receive and perform vector quantization of a first dataset. The multiscale quantization model can generate a residual dataset based at least in part on a result of the vector quantization. The multiscale quantization model can apply a rotation matrix to the residual dataset to generate a rotated residual dataset that includes a plurality of rotated residuals. The multiscale quantization model can perform reparameterization of each rotated residual in the rotated residual dataset into a direction component and a scale component. The multiscale quantization model can perform product quantization of the direction components of the plurality of rotated residuals, and perform scalar quantization of the scale components of the plurality of rotated residuals.

Abstract: A multi-area artificial fog pipe network control method and system based on a YOLOv5 algorithm are provided. The method includes: obtaining thermal sensation data of each target person based on facial skin temperature; calculating group thermal sensation data of each subarea and total group thermal sensation data of an artificial fog pipe network area; determining a total flow of fog-making water introduced into the artificial fog pipe network according to target number of people and total group thermal sensation data; controlling opening gears of atomization nozzles on the artificial fog pipe networks in subareas according to a number of the target person in each subarea, the group thermal sensation data and a micro-action type of each target person. The method can realize purposes of saving energy, reducing emission, accurately controlling the flow of the fog-making water, and the people-oriented aim and outdoor group heat comfort maximization.

Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a multiscale quantization model that is configured to provide a quantized dataset. In particular, the multiscale quantization model can receive and perform vector quantization of a first dataset. The multiscale quantization model can generate a residual dataset based at least in part on a result of the vector quantization. The multiscale quantization model can apply a rotation matrix to the residual dataset to generate a rotated residual dataset that includes a plurality of rotated residuals. The multiscale quantization model can perform reparameterization of each rotated residual in the rotated residual dataset into a direction component and a scale component. The multiscale quantization model can perform product quantization of the direction components of the plurality of rotated residuals, and perform scalar quantization of the scale components of the plurality of rotated residuals.

Abstract: A systems and method for providing various improvements in the computing time and accuracy for finding items using a hybrid vector space inner-product search are described.

Abstract: Techniques of indexing a database and processing a query involve decomposing the residual term according to a projection matrix that is based on a given direction v. For example, for each database element of a partition, the residual for that database element is split into a component parallel to a given direction and a component perpendicular to that direction. The parallel component lies in a one-dimensional subspace spanned by the direction and may be efficiently quantized with a scalar quantization. The perpendicular component is quantized using multiscale quantization techniques. The quantized residual components and the center elements of each partition define the indexed database. Upon receipt of a query from a user, the inner products of q with the residual may be computed efficiently using the quantized residual components. From these inner products, the database elements that are most similar to the query are selected and returned to the user.

Abstract: Generally, the present disclosure is directed to systems and methods of quantizing a database with respect to a novel loss or quantization error function which applies a weight to an error measurement of quantized elements respectively corresponding to the datapoints in the database. The weight is determined based on the magnitude of an inner product between the respective datapoints and a query compared therewith. In contrast to previous work, embodiments of the proposed loss function are responsive to the expected magnitude of an inner product between the respective datapoints and a query compared therewith and can prioritize error reduction for higher-ranked pairings of the query and the datapoints. Thus, the systems and methods of the present disclosure provide solutions to some of the problems with traditional quantization approaches, which regard all error as equally impactful.

Abstract: The present disclosure provides systems and methods that perform stochastic generative hashing. According to one example aspect, a machine-learned hashing model that generates a binary hash for an input can be trained in conjunction with a machine-learned generative model that reconstructs the input from the binary hash. The present disclosure provides a novel generative approach to learn hash functions through Minimum Description Length principle such that the learned hash codes maximally compress the dataset. According to another example aspect, the present disclosure provides an efficient learning algorithm based on the stochastic distributional gradient, which avoids the notorious difficulty caused by binary output constraints, to jointly optimize the parameters of the hashing model and the associated generative model.

Abstract: Techniques of indexing a database and processing a query involve decomposing the residual term according to a projection matrix that is based on a given direction v. For example, for each database element of a partition, the residual for that database element is split into a component parallel to a given direction and a component perpendicular to that direction. The parallel component lies in a one-dimensional subspace spanned by the direction and may be efficiently quantized with a scalar quantization. The perpendicular component is quantized using multiscale quantization techniques. The quantized residual components and the center elements of each partition define the indexed database. Upon receipt of a query from a user, the inner products of q with the residual may be computed efficiently using the quantized residual components. From these inner products, the database elements that are most similar to the query are selected and returned to the user.

Abstract: Implementations provide an efficient system for calculating inner products between high-dimensionality vectors. An example method includes clustering database items represented as vectors, selecting a cluster center for each cluster, and storing the cluster center as an entry in a first layer codebook. The method also includes, for each database item, calculating a residual based on the cluster center for the cluster the database item is assigned to and projecting the residual into subspaces. The method also includes determining, for each of the subspaces, an entry in a second layer codebook for the subspace, and storing the entry in the first layer codebook and the respective entry in the second layer codebook for each of the subspaces as a quantized vector for the database item. The entry can be used to categorize an item represented by a query vector or to provide database items responsive to a query vector.

Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a multiscale quantization model that is configured to provide a quantized dataset. In particular, the multiscale quantization model can receive and perform vector quantization of a first dataset. The multiscale quantization model can generate a residual dataset based at least in part on a result of the vector quantization. The multiscale quantization model can apply a rotation matrix to the residual dataset to generate a rotated residual dataset that includes a plurality of rotated residuals. The multiscale quantization model can perform reparameterization of each rotated residual in the rotated residual dataset into a direction component and a scale component. The multiscale quantization model can perform product quantization of the direction components of the plurality of rotated residuals, and perform scalar quantization of the scale components of the plurality of rotated residuals.

Abstract: A systems and method for providing various improvements in the computing time and accuracy for finding items using a hybrid vector space inner-product search are described.