Abstract: Embodiments include methods, and processing devices for implementing the methods. Various embodiments may include calculating a batch softmax normalization factor using a plurality of logit values from a plurality of logits of a layer of a neural network, normalizing the plurality of logit values using the batch softmax normalization factor, and mapping each of the normalized plurality of logit values to one of a plurality of manifolds in a coordinate space. In some embodiments, each of the plurality of manifolds represents a number of labels to which a logit can be classified. In some embodiments, at least one of the plurality of manifolds represents a number of labels other than one label.

Abstract: A method for labeling a spherical target includes receiving an input including a representation of an object. The method also includes estimating unconstrained coordinates corresponding to the object. The method further includes estimating coordinates on a sphere by applying a spherical exponential activation function to the unconstrained coordinates. The method also associates the input with a set of values corresponding to a spherical target based on the estimated coordinates on the sphere.

Abstract: A method aligns, with an artificial neural network, a three-dimensional (3D) model to an object in a 2D image. The method includes detecting, with an object detector, the object from the 2D image. The method also includes estimating a geodesic distance value between the object and multiple discretized poses of the 3D model. The method further includes selecting a discretized pose of the multiple discretized poses corresponding to a smallest geodesic distance value. The method still further includes propagating pose parameters of the selected discretized pose of the 3D model to the object.

Abstract: A method for labeling a spherical target includes receiving an input including a representation of an object. The method also includes estimating unconstrained coordinates corresponding to the object. The method further includes estimating coordinates on a sphere by applying a spherical exponential activation function to the unconstrained coordinates. The method also associates the input with a set of values corresponding to a spherical target based on the estimated coordinates on the sphere.

Abstract: A method aligns, with an artificial neural network, a three-dimensional (3D) model to an object in a 2D image. The method includes detecting, with an object detector, the object from the 2D image. The method also includes estimating a geodesic distance value between the object and multiple discretized poses of the 3D model. The method further includes selecting a discretized pose of the multiple discretized poses corresponding to a smallest geodesic distance value. The method still further includes propagating pose parameters of the selected discretized pose of the 3D model to the object.

Abstract: A management system for a plurality of hard disk drives which gives disk-specific information includes a storage unit and a processor. The storage unit is configured to couple to the plurality of hard disk drives and includes an information module configured to store identification information of each hard disk drive and a checking module configured to check status of each hard disk drive according to a location information in the identification and send out an error warning if in error status. The processor is coupled to the storage unit and obtains the identification information and error warnings. The error warning comprises the identification information and an error type of the error hard disk drive. An electronic device with the management system is further provided.