3 results about "Matrix addition" patented technology

Aspects of the present invention are directed to computer-implemented techniques for improving the training of artificial neural networks using a reduced precision (e.g., float16) data format. Embodiments of the present invention rescale tensor values prior to performing matrix operations (such as matrix multiplication or matrix addition) to prevent overflow and underflow. To preserve accuracy throughout the performance of the matrix operations, the scale factors are defined using a novel data format to represent tensors, wherein a matrix is represented by the tuple X, where X=(a, v[.]), wherein a is a float scale factor and v[.] are scaled values stored in the float16 format. The value of any element X[i] according to this data format would be equal to a*v[i].

The invention relates to a storage and calculation integrated peripheral circuit device based on a 3D VRRAM and a matrix calculation method, belongs to the technical field of memories, and solves the problem that the structure of an existing two-dimensional resistive random access memory array is not suitable for a neural network with a high calculation power demand. The device comprises a matrix multiplier for multiplying an input data matrix by a weight matrix; the input ends of the analog-to-digital converters are connected to the output ends of the column control switches so as to convert the analog product result into a digital product result; the plurality of samplers are connected with the output end of the analog-to-digital converter so as to sample the digital product result; the output ends of the plurality of samplers are connected with the input end of the matrix adder through the matrix adder so as to realize digital product result shifting, then shifting data are accumulated, and an accumulation result is stored in a temporary register; and the updating register adds the accumulation result and the data in the updating register to obtain sum data, and updates the data in the updating register by using the sum data. And high-storage and high-computing-power-density operation is realized so as to be suitable for a neural network.

The application discloses a sintering endpoint prediction method, device, equipment and readable storage medium, obtains to-be-processed data, divides the to-be-processed data into t moments, obtains a feature vector based on the to-be-processed data of the current moment, obtains a factor attention result based on the feature vector and a hidden vector of the previous moment, determines a time attention result, calculates a new feature vector through matrix addition of the feature vector and the time attention result, obtains the hidden vector of the current moment and a prediction result of the current moment based on the new feature vector, judges whether the current moment is the t moment, if not, the next moment is a new current moment, and the step of constructing an adjacency matrix based on the to-be-processed data is returned to be executed, and if yes, a final prediction result is determined based on the t prediction results. In the application, the factor time attention is focused, the contribution of each variable and each time to the prediction is captured, and the accuracy of predicting the sintering endpoint is improved to a certain extent.