Ikanos Communications, Inc.

Wave Computing, Inc.

Sylvain Flamant

Echere Iroaga

Qasem Aldrubi

Jason C Hu

Techniques for a neural network output layer for machine learning are disclosed. A plurality of processing elements within a reconfigurable fabric is configured to implement a data flow graph, where the data flow graph implements a neural network. The data flow graph can include machine learning or deep learning. A layer is implemented, within the neural network, that maps a first vector of real values to a second vector of real values bounded by zero and one, where the second vector sums to a value of one using fixed-point calculations. The layer can include a final layer within the neural network. The layer that maps the first vector includes a Softmax function. Results of the neural network are classified based on a value of the second vector. The classifying can include part of a machine learning or a deep learning process.

Neural network output layer for machine learning

Peak-to-average ratio reduction is achieved by detecting peaks in an original analog signal that exceed a given threshold. Segments of the original analog signal containing such peaks are treated (e.g., by attenuation) and a composite analog signal is assembled that includes treated and untreated segments of the original analog signal. The composite analog signal is processed to perform analog-to-digital conversion to generate a composite digital signal. Segments of the composite digital signal corresponding to the treated segments of the original analog signal are reverse-treated or otherwise treated again to undo treatment of the segments of the original analog signal. A final output digital signal is generated that corresponds to the original analog signal in digital form.

Growing community of inventors

Saratoga, CA, United States of America

Sylvain Flamant