TensorNetwork for Machine Learning
We demonstrate the use of tensor networks for image classification with the TensorNetwork open source library. We explain in detail the encoding of image data into a matrix product state form, and describe how to contract the network in a way that is parallelizable and well-suited to automatic gradients for optimization. Applying the technique to the MNIST and Fashion-MNIST datasets we find out-of-the-box performance of 98% and 88% accuracy, respectively, using the same tensor network architecture. The TensorNetwork library allows us to seamlessly move from CPU to GPU hardware, and we see a factor of more than 10 improvement in computational speed using a GPU.
Code (1)
Tasks
BIG-bench Machine LearningCPUGeneral ClassificationGPUimage-classificationImage ClassificationTensor NetworksMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TensorNetwork: A Library for Physics and Machine Learning
TensorNetwork is an open source library for implementing tensor network algorithms. Tensor networks are sparse data structures originally designed for simulating quantum many-body physics, but are currently also applied …
BIG-bench Machine LearningTensor NetworksTensorNetwork on TensorFlow: A Spin Chain Application Using Tree Tensor Networks
TensorNetwork is an open source library for implementing tensor network algorithms in TensorFlow. We describe a tree tensor network (TTN) algorithm for approximating the ground state of either a periodic quantum spin cha…
GPUTensor NetworksSymbolically integrating tensor networks over various random tensors by the second version of Python RTNI
We are upgrading the Python-version of RTNI, which symbolically integrates tensor networks over the Haar-distributed unitary matrices. Now, PyRTNI2 can treat the Haar-distributed orthogonal matrices and the real and comp…
Tensor NetworksNewtonian Mechanics Based Transient Stability PART VI: Machine Transformation
This paper focuses on the transformations from the individual machine to the equivalent machine through the "correction" perspective of the inner-group machine. The machines are first classified as the real machine with …
Newtonian Mechanics Based Transient Stability PART I: Machine Paradigms
Individual-machine, superimposed-machine and equivalent-machine can be seen as the three major perspectives of the power system transient stability. In this paper, the machine paradigms are established according to the c…