Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

awesome-tensorial-neural-networks

A thoroughly investigated survey for tensorial neural networks.
https://github.com/tnbar/awesome-tensorial-neural-networks

Last synced: 3 days ago
JSON representation

  • Network compression via TNNs

    • Tensorial Convolutional Neural Networks

      • [link - task deep models. | ICONIP | 2020 |
      • [link - time evaluation of large convolutional networks via CP-decomposition. | NeurIPS | 2014 |
      • [link - Based Systems | 2022 |
      • [link - HigherOrder Convolution (HO-CPConv), to spatio-temporal facial emotion analysis. | CVPR | 2020 |
      • [link - EPC is proposed with a minimal sensitivity design for both CP convolutional layers and hybrid Tucker2-CP convolutional layers. | ECCV | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - rank tucker tensor format. | CVPR | 2019 |
      • [link
      • [link
      • [link - task Tucker models and Tensor Train modesl that learn cross-task sharing structure. | ICLR | 2017 |
      • [link
      • [link - connected layers in CNNs to the Tensor Train format. | NeurIPS | 2015 |
      • [link - decomposition. | ICLR | 2015 |
      • [link - time evaluation of large convolutional networks via CP-decomposition. | NeurIPS | 2014 |
      • [link
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - rank Block-Term Tucker tensors. | Neural Networks | 2020 |
      • [link
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - decomposition. | ICLR | 2015 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |
      • [link - task deep models. | ICONIP | 2020 |

    • Tensorial Recurrent Neural Networks

      • [link
      • [link
      • [link
      • [link - rank Block-Term Tucker tensors. | Neural Networks | 2020 |
      • [link - train module that performs prediction by combining convolutional features across time. | NeurIPS | 2020 |
      • [link - parameterize the Gated Recurrent Unit (GRU) RNN. | IEICE Transactions on Information and Systems | 2019 |
      • [link - LSTM, by utilizing the low-rank tensor ring decomposition (TRD) to reformulate the input-to-hidden transformation. | AAAI | 2019 |
      • [link
      • [link - Term tensor decomposition to reduce the parameters of RNNs and improves their training efficiency. | CVPR | 2018 |
      • [link - to-hidden weight matrix in RNNs using Tensor-Train decomposition. | ICML | 2017 |
      • [link - to-end trainable neural network layers. | CVPR-Workshop | 2017 |

    • Tensorial Transformer

      • [link - MPO) to grow a small pretrained model to a large counterpart for efficient training. | NeurIPS | 2023 |
      • [link
      • [link - driven weights across heads via low rank tensor diagrams. | ICLR | 2022 |
      • [link
      • [link
      • [link - tuning strategy by only updating the parameters from the auxiliary tensors, and design an optimization algorithm for MPO-based approximation over stacked network architectures. | ACL/IJCNLP | 2021 |
      • [link - attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition. | NeurIPS | 2019 |
      • [link - MPO) to grow a small pretrained model to a large counterpart for efficient training. | NeurIPS | 2023 |

    • Tensorial Graph Neural Networks

      • [link - order non-linear node interactions. | NeurIPS | 2022 |
      • [link
      • [link

    • Tensorial Restricted Boltzmann Machine

      • [link
      • [link - input RBM model, which employs the tensor-ring (TR) decomposition structure to naturally represent the high-order relationship. | IJCNN | 2019 |
      • [link
      • [link

  • Information Fusion via TNNs

    • Tensor Fusion Layer-Based Methods

      • [link - order moments. | NeurIPS | 2019 |
      • [link - rank method, which performs multimodal fusion using low-rank tensors to improve efficiency. | ACL | 2018 |
      • [link - modality and inter-modality dynamics. | EMNLP | 2017 |

    • Multimodal Pooling-Based Methods

      • [link
      • [link - rank bilinear pooling using Hadamard product for an efficient attention mechanism of multimodal learning. | Arxiv preprint | 2016 |
      • [link - based Tucker decomposition to efficiently parametrize bilinear interactions between visual and textual representations. | CVPR | 2017 |

  • Training Strategy

  • Quantum Circuit Simulation on TNNs

    • Quantum Embedded Data Processing

      • [link - body physics and autoregressive modeling from machine learning. | Physical Review E | 2023 |
      • [link
      • [link - inspired tensor networks to image classification. | NeurIPS | 2016 |
      • [link - dimensional) entangled quantum states. | Physical Review X | 2018 |
      • [link - MPS the ability to efficiently sample from a wide variety of conditional distributions, each one defined by a regular expression. | AISTATS | 2021 |

    • Convolutional Arithmetic Circuits

      • [link
      • [link - use of information in the network operation as a key trait which distinguishes them from standard Tensor Network based representations. | PRL | 2019 |
      • [link - body wave function. | ICLR | 2018 |
      • [link - 1) decomposition, whereas a deep network corresponds to Hierarchical Tucker decomposition. | COLT | 2016 |
      • [link

  • Toolboxes

    • Basic Tensor Operation

      • Tensorly - source, actively maintained and easily extensible. TensorLy provides all the utilities to easily use tensor methods from core tensor operations and tensor algebra to tensor decomposition and regression. | Python (NumPy, PyTorch, TensorFlow, JAX, Apache MXNet and CuPy) |
      • TensorD

    • Deep Model Implementation

      • Tensorly-Torch - Torch is a PyTorch only library that builds on top of [TensorLy](http://tensorly.org/dev) and provides out-of-the-box tensor layers. It comes with all batteries included and tries to make it as easy as possible to use tensor methods within your deep networks. | Python (Pytorch) |

    • Quantum Tensor Simulation

Categories
Network compression via TNNs 65 Training Strategy 41 Quantum Circuit Simulation on TNNs 10 Toolboxes 6 Information Fusion via TNNs 6
Sub Categories
Tensorial Convolutional Neural Networks 39 Rank Selection 37 Tensorial Recurrent Neural Networks 11 Tensorial Transformer 8 Quantum Embedded Data Processing 5 Convolutional Arithmetic Circuits 5 Tensorial Restricted Boltzmann Machine 4 Tensor Fusion Layer-Based Methods 3 Quantum Tensor Simulation 3 Hardware Training 3 Tensorial Graph Neural Networks 3 Multimodal Pooling-Based Methods 3 Basic Tensor Operation 2 Deep Model Implementation 1 Stable Training 1