Efficient and accurate neural field reconstruction using resistive memory

Machine Learning


  • Sitzmann, V., Martel, J., Bergman, A., Lindell, D. & Wetzstein, G. Implicit neural representations through periodic activation functions. in Procedures 34th International Conference on Neural Information Processing Systems 7462–7473 (ACM, 2020).

  • Liu, R., Sun, Y., Zhu, J., Tian, ​​L. & Kamilov, USA Recovery of continuous 3D refractive index maps from discrete intensity-only measurements using neural fields. nut. Mach. intelligence. 4781–791 (2022).

    Article Google Scholar

  • Shen, H. et al. Reconstruction of missing information in remote sensing data: A technical review. IEEE Earth Sciences. remote sensor mug. 361–85 (2015).

    Article Google Scholar

  • Mildenhall, B. et al. NeRF: Representing scenes as neural radiance fields for view synthesis. common. ACM 6599–106 (2021).

    Article Google Scholar

  • Bartolozzi, C., Indiveri, G., Donati, E. Embodied neuromorphic intelligence. nut. common. 131024 (2022).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Santos, JE et al. Development of Sensever for efficient field reconstruction from sparse observations. nut. Mach. intelligence. 51317–1325 (2023).

    Article Google Scholar

  • Tononi, G., Edelman, GM, Sporns, O. Complexity and coherence: Integrating information in the brain. Trends Cognition Science. 2474–484 (1998).

    Article CAS PubMed Google Scholar

  • Schafer, RW & Rabiner, LR Digital representation of audio signals. procedure IEEE 63662–677 (1975).

    Article ADS Google Scholar

  • Rabbani, M. & Jones, P.W. Digital image compression technology Vol. TT7 (SPIE Optical Engineering Press, 1991).

  • Wu, Z. et al. 3D ShapeNet: Detailed representation of volumetric shapes. in IEEE Conference on Procedural Computer Vision and Pattern Recognition 1912-1920 (IEEE, 2015).

  • Karni, Z. & Gotsman, C. Spectral compression of mesh geometries. in Procedures 27th Annual Conference on Computer Graphics and Interactive Technologies 279–286 (IEEE, 2000).

  • Qi, CR, Su, H., Mo, K., Guibas, LJ Pointnet: Deep learning of point sets for 3D classification and segmentation. in IEEE Conference on Procedural Computer Vision and Pattern Recognition 652–660 (IEEE, 2017).

  • Lin, L., Liao, X., Jin, H., Li, P. Computational offloading towards edge computing. procedure IEEE 1071584–1607 (2019).

    Article ADS Google Scholar

  • Han, S., Mao, H. & Dally, WJ Deep compression: Compressing deep neural networks using pruning, trained quantization, and Huffman coding. in Procedure 4th International Conference on Learning Representations (ICLR, 2016).

  • Horowitz, M. 1.1 The energy problem of computing (and what we can do about it). in Procedure 2014 IEEE International Solid State Circuits Conference Technical Paper Digest (ISSCC) 10–14 (IEEE, 2014).

  • Zidane, MA, JP Strachan & WD Lou The future of electronics based on memristive systems. nut. electronic. 122–29 (2018).

    Article Google Scholar

  • Wong, H.-SP and Salahuddin, S. Memory leads the way to better computing. nut. nanotechnology. 10191–194 (2015).

    Article ADS CAS PubMed Google Scholar

  • Chen, Y., Xie, Y., Song, L., Chen, F., Tang, T. A survey of accelerator architectures for deep neural networks. engineering 6264–274 (2020).

    Article Google Scholar

  • Hinton, G. How to represent part-whole hierarchies with neural networks. neural computing. 35413–452 (2023).

    Article MathSciNet PubMed Google Scholar

  • Jaderberg, M., Vedaldi, A. & Zisserman, A. Accelerating convolutional neural networks with low-rank expansion. in Procedures British Machine Vision Conference (BMVA Press, 2014).

  • Denil, M., Shakibi, B., Dinh, L., Ranzato, M., de Freitas, N. Parameter prediction in deep learning. in Advances in procedural neural information processing systems (NeurIPS, 2013).

  • Fang, G., Ma, X., Song, M., Mi, MB & Wang, X. Depgraph: Towards any structural pruning. in IEEE/CVF Conference on Procedural Computer Vision and Pattern Recognition 16091–16101 (IEEE, 2023).

  • Ambrogio, S. et al. Using analog memory to accelerate neural network training with comparable accuracy. nature 55860–67 (2018).

    Article ADS CAS PubMed Google Scholar

  • Ambrogio, S. et al. Analog AI chips for energy-efficient speech recognition and transcription. nature 620768–775 (2023).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Wang, W. et al. Compute-in-memory chips based on resistive random access memory. nature 608504–512 (2022).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Wang, Z. et al. Memristor with diffusion dynamics as a synapse emulator for neuromorphic computing. nut. meter. 16101–108 (2017).

    Article CAS PubMed Google Scholar

  • Zhang, W. et al. Edge learning using a fully integrated neuro-inspired memristor chip. science 3811205–1211 (2023).

    Article ADS CAS PubMed Google Scholar

  • Yao, P. et al. A fully hardware implemented memristor convolutional neural network. nature 577641–646 (2020).

    Article ADS CAS PubMed Google Scholar

  • Xia, Q., Yang, JJ Memristive crossbar arrays for brain-inspired computing. nut. meter. 18309–323 (2019).

    Article CAS PubMed Google Scholar

  • Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R., Eleftheriou, E. Memory devices and applications for in-memory computing. nut. nanotechnology. 15529–544 (2020).

    Article ADS CAS PubMed Google Scholar

  • Song, L., Qian, X., Li, H. & Chen, Y. Pipelayer: A pipelined ReRam-based accelerator for deep learning. in Procedures 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA) 541–552 (IEEE, 2017).

  • Ielmini, D. & Wong, H.-SP In-memory computing using resistive switching devices. nut. electronic. 1333–343 (2018).

    Article Google Scholar

  • Rao, M. et al. Thousands of conductance levels of memristors integrated on CMOS. nature 615823–829 (2023).

    Article ADS CAS PubMed Google Scholar

  • Yi, S.-in, Kendall, JD, Williams, RS, and Kumar, S. Activity-differential training of deep neural networks using memristor crossbars. nut. electronic. 645–51 (2023).

    Google Scholar

  • Kumar, S., Wang, X., Strachan, JP, Yang, Y. & Lu, WD Dynamic memristors for more complex neuromorphic computing. nut. Pastor Mater. 7575–591 (2022).

    Article Google Scholar

  • Prezioso, M. et al. Training and operation of integrated neuromorphic networks based on metal oxide memristors. nature 52161–64 (2015).

    Article ADS CAS PubMed Google Scholar

  • Sun, Z., Pedretti, G., Bricalli, A. & Ielmini, D. One-step regression and classification using crosspoint resistive memory arrays. Science. advanced 6eaay2378 (2020).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Yuan, R. et al. A VO2 memristor-based neuromorphophysiological signal processing system for next-generation human-machine interfaces. nut. common. 143695 (2023).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • Cai, F. et al. Power-efficient combinatorial optimization using intrinsic noise in memristor hop-field neural networks. nut. electronic. 3409–418 (2020).

    Article Google Scholar

  • Wang, S. et al. Echo state graph neural network with analog random resistive memory array. nut. Mach. intelligence. 5104–113 (2023).

    Article Google Scholar

  • Yang, Y et al. Observation of conductive filament growth in nanoscale resistive memory. nut. common. 3732 (2012).

    Article ADS PubMed Google Scholar

  • Banner, R., Nahshan, Y., and Soudry, D. Post-training 4-bit quantization of convolutional networks for rapid deployment. in Advances in procedural neural information processing systems 7950–7958 (NeurIPS, 2019).

  • Jacob, B. et al. Quantizing and training neural networks for efficient integer-only inference. in 2018 IEEE/CVF Conference on Procedural Computer Vision and Pattern Recognition 2704–2713 (IEEE, 2018).

  • Jacot, A., Gabriel, F., Hongler, C. Neural tangent kernels: Convergence and generalization of neural networks. in Advances in procedural neural information processing systems 8580–8589 (NeurIPS, 2018).

  • Vaswani, A. et al. All you need is attention. in Advances in procedural neural information processing systems 6000–6010 (NeurIPS, 2017).

  • Tancik, M. et al. Fourier functions allow networks to learn high-frequency functions in low-dimensional domains. in Advances in procedural neural information processing systems 7537–7547 (NeurIPS, 2020).

  • Volder, JE CORDIC trigonometric calculation techniques. IRE transformer. electronic. Calculate. EC-8330–334 (1959).

    Article Google Scholar

  • Chen, G.-H., Tang, J. & Leng, S. Pre-Image Constrained Compressed Sensing (PICCS): A method for accurately reconstructing dynamic CT images from highly undersampled projection data sets. medicine. Physics. 35660–663 (2008).

    Article PubMed PubMed Central Google Scholar

  • Sidky, E.Y., Cao, C.-M. & Pan, X. Accurate image reconstruction from a small number of views and limited angle data in divergent beam CT. J. Xray Sci. Technology. 14119–139 (2006).

    Google Scholar

  • Shen, L., Pauly, J. & Xing, L. NeRP: Implicit neural representation learning with preembedding for sparsely sampled image reconstruction. in IEEE Transactions on Procedural Neural Networks and Learning Systems 770–782 (IEEE, 2022).

  • Eslami, SMA et al. Neural scene representation and rendering. science 3601204–1210 (2018).

    Article ADS CAS PubMed Google Scholar

  • Kerbl, B., Kopanas, G., Leimkühler, T. & Drettakis, G. 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. graph. 42139 (2023).

    Article Google Scholar

  • Pumarola, A., Corona, E., Pons-Moll, G. & Moreno-Noguer, F. D-NeRF: Neural radiation fields of dynamic scenes. in IEEE/CVF Conference on Procedural Computer Vision and Pattern Recognition 10318–10327 (IEEE, 2021).

  • Horé, A. & Ziou, D. Image quality metrics: PSNR and SSIM. in Procedure 2010 20th International Conference on Pattern Recognition 2366–2369 (IEEE, 2010).

  • Zhang, R., Isola, P., Efros, AA, Shechtman, E. & Wang, O. The irrational effectiveness of deep features as perceptual indicators. in IEEE Conference on Procedural Computer Vision and Pattern Recognition 586–595 (IEEE, 2018).

  • Yu, Y. Memristive neural area. GitHub https://github.com/SuperFrankyy/Memristive_Neural_Field (2026).



  • Source link