Abstract: A system classifies a compressed image or predicts likelihood values associated with a compressed image. The system partially decompresses compressed JPEG image data to obtain blocks of discrete cosine transform (DCT) coefficients that represent the image. The system may apply various transform functions to the individual blocks of DCT coefficients to resize the blocks so that they may be input together into a neural network for analysis. Weights of the neural network may be trained to accept transformed blocks of DCT coefficients which may be less computationally intensive than accepting raw image data as input.

Abstract: Machine learning based models, for example, neural network models employ large numbers of parameters, from a few million to hundreds of millions or more. A machine learning based model is trained using fewer parameters than specified. An initial parameter vector is initialized, for example, using random number generation based on a seed. During training phase, the parameter vectors are modified in a subspace around the initial vector. The trained model can be stored or transmitted using seed values and the trained parameter vector in the subspace. The neural network model can be uncompressed using the seed values and the trained parameter vector in the subspace. The compressed representation of neural networks may be used for various applications such as generating maps, object recognition in images, processing of sensor data, natural language processing, and others.

Abstract: A system classifies a compressed image or predicts likelihood values associated with a compressed image. The system partially decompresses compressed JPEG image data to obtain blocks of discrete cosine transform (DCT) coefficients that represent the image. The system may apply various transform functions to the individual blocks of DCT coefficients to resize the blocks so that they may be input together into a neural network for analysis. Weights of the neural network may be trained to accept transformed blocks of DCT coefficients which may be less computationally intensive than accepting raw image data as input.

Abstract: Machine learning based models, for example, neural network models employ large numbers of parameters, from a few million to hundreds of millions or more. A machine learning based model is trained using fewer parameters than specified. An initial parameter vector is initialized, for example, using random number generation based on a seed. During training phase, the parameter vectors are modified in a subspace around the initial vector. The trained model can be stored or transmitted using seed values and the trained parameter vector in the subspace. The neural network model can be uncompressed using the seed values and the trained parameter vector in the subspace. The compressed representation of neural networks may be used for various applications such as generating maps, object recognition in images, processing of sensor data, natural language processing, and others.