논문 및 사진 출처 Baevski, Alexei, et al. “Efficient self-supervised learning with contextualized target representations for vision, speech and language.” International Conference on Machine Learning. PMLR, 2023.

출처 Yan, Zhicheng, et al. “HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition.” Proceedings of the IEEE international conference on computer vision. 2015.

논문 및 사진 출처 Peyser, Cal, et al. “A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale.” ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023.

1 epoch 도는데 너무 오래걸려서 그 후에 발생하는 오류를 확인하는데까지 시간이 너무 오래 걸릴 때 사용하면 좋은 방법

논문 및 사진 출처 Han, Meng, et al. “QuickFPS: Architecture and Algorithm Co-Design for Farthest Point Sampling in Large-Scale Point Clouds.” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2023).

논문 및 사진 출처 Gong, Yuan, et al. “Contrastive audio-visual masked autoencoder.” arXiv preprint arXiv:2210.07839 (2022)..

\lib\site-packages\torch\utils\data_utils[collate.py](http://collate.py/)”, line 141, in default_collate return torch.stack(batch, 0, out=out) RuntimeError: stack expects each tensor to be equal size, but got [1, 5985] at entry 0 and [234, 5985] at entry 1

출처 Klapsas, Konstantinos, et al. “Self supervised learning for robust voice cloning.” arXiv preprint arXiv:2204.03421 (2022).

출처 Du, Ye-Qian, et al. “A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition.” arXiv preprint arXiv:2204.02023 (2022). Copyright of figures and other materials in the paper belongs to original authors.

1. FMS / CIM, ERP, MES, PLM, SCM, SCADA, DCS.