Incorporating top-down information in deep neural networks via the bias term

    公开(公告)号:AU2016256315A1

    公开(公告)日:2017-10-05

    申请号:AU2016256315

    申请日:2016-03-11

    Applicant: QUALCOMM INC

    Abstract: A method of biasing a deep neural network includes determining whether an element has an increased probability of being present in an input to the network. The method also includes adjusting a bias of activation functions of neurons in the network to increase sensitivity to the element. In one configuration, the bias is adjusted without adjusting weights of the network. The method further includes adjusting an output of the network based on the biasing.

    ENFORCED SPARSITY FOR CLASSIFICATION

    公开(公告)号:CA2993011A1

    公开(公告)日:2017-03-09

    申请号:CA2993011

    申请日:2016-08-04

    Applicant: QUALCOMM INC

    Abstract: An apparatus for classifying an input includes a classifier and a feature extractor. The feature extractor is configured to generate a feature vector based on the input. The feature vector is also configured to set a number of elements of the feature vector to zero to produce a sparse feature vector. The sparse feature vector has the same dimensions as the feature vector generated by the feature extractor. However, the sparse feature vector includes fewer non-zero elements than the feature vector generated by the feature extractor. The feature vector is further configured to forward the sparse feature vector to the classifier to classify the input.

    BLINK AND AVERTED GAZE AVOIDANCE IN PHOTOGRAPHIC IMAGES

    公开(公告)号:CA2938135A1

    公开(公告)日:2015-09-17

    申请号:CA2938135

    申请日:2015-02-27

    Applicant: QUALCOMM INC

    Abstract: A method of blink and averted gaze avoidance with a camera includes detecting an averted gaze of a subject and/or one or more closed eyes of the subject in response to receiving an input to actuate a camera shutter. The method also includes scheduling actuation of the camera shutter to a future estimated time period to capture an image of the subject when a gaze direction of the subject is centered on the camera and/or both eyes of the subject are open.

    DIFFERENTIAL ENCODING IN NEURAL NETWORKS
    10.
    发明申请
    DIFFERENTIAL ENCODING IN NEURAL NETWORKS 审中-公开
    神经网络中的差分编码

    公开(公告)号:WO2015148189A3

    公开(公告)日:2015-12-17

    申请号:PCT/US2015021077

    申请日:2015-03-17

    Applicant: QUALCOMM INC

    CPC classification number: G06N3/0445 G06N3/0481 G06N3/049

    Abstract: Differential encoding in a neural network includes predicting an activation value for a neuron in the neural network based on at least one previous activation value for the neuron. The encoding further includes encoding a value based on a difference between the predicted activation value and an actual activation value for the neuron in the neural network.

    Abstract translation: 神经网络中的差分编码包括基于神经元的至少一个先前激活值来预测神经网络中神经元的激活值。 编码还包括基于预测的激活值和神经网络中的神经元的实际激活值之间的差来编码值。

Patent Agency Ranking