পদ্ধতির তুলনা করুন

	Autoformer: দীর্ঘমেয়াদী সময়-সিরিজ পূর্বাভাসের জন্য ডিকম্পোজিশন ট্রান্সফরমার	দীর্ঘ অনুক্রমের জন্য কার্যকর ট্রান্সফরমার: রিফর্মার
ক্ষেত্র	গভীর শিখন	গভীর শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	2021	2020
প্রবর্তক	Haixu Wu et al. (Tsinghua)	Nikita Kitaev, Łukasz Kaiser & Anselm Levskaya
ধরন	Decomposition-based deep forecasting model	Memory-efficient attention-based sequence model
মৌলিক উৎস	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Kitaev, N., Kaiser, Ł., & Levskaya, A. (2020). Reformer: The efficient transformer. ICLR.
অপর নাম	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Efficient Transformer, LSH Transformer, Locality-Sensitive Hashing Transformer, Verimli Dönüştürücü
সম্পর্কিত	4	2
সারসংক্ষেপ	Autoformer is a deep learning architecture for long-term time-series forecasting, introduced by Wu et al. from Tsinghua University at NeurIPS 2021. It replaces the standard self-attention mechanism with an Auto-Correlation mechanism that exploits periodic dependencies in the frequency domain, and embeds a progressive series decomposition block throughout the encoder and decoder to separately model trend and seasonal components.	The Reformer is an efficient variant of the Transformer architecture introduced by Kitaev, Kaiser, and Levskaya at ICLR 2020. It addresses the prohibitive O(L²) memory and computational cost of standard self-attention for long sequences. The key innovations are locality-sensitive hashing (LSH) attention, which approximates full attention in O(L log L) time, and reversible residual layers that dramatically reduce activation memory during training.