2026-01-27 東京大学 国際高等研究所
図1 ESNにおける入力再構成の定式化
上段：ESNの典型的な定式化。入力層・リザバー層・出力層から構成され、リザバー層から出力層への結合行列は教師データに基づき学習されます。入力再構成タスクにおいても、真の入力系列そのものを教師データとして与える必要がありました。
下段：本研究による再定式化。特定の数学的条件が成り立つ場合、教師データを用いずにリザバー状態の系列のみから入力再構成を実現可能であることを示しました。
＜関連情報＞
- https://ircn.jp/pressrelease/20260127_kantaro_fujiwara
- https://direct.mit.edu/neco/article-abstract/38/2/198/133752/Unsupervised-Learning-in-Echo-State-Networks-for
入力再構成のためのエコー状態ネットワークにおける教師なし学習 Unsupervised Learning in Echo State Networks for Input Reconstruction
Taiki Yamada,Yuichi Katori,Kantaro Fujiwara
Neural Computation Published:January 20 2026
DOI:https://doi.org/10.1162/NECO.a.38
Abstract
Echo state networks (ESNs) are a class of recurrent neural networks in which only the readout layer is trainable, while the recurrent and input layers are fixed. This architectural constraint enables computationally efficient processing of time-series data. Traditionally, the readout layer in ESNs is trained using supervised learning with target outputs. In this study, we focus on input reconstruction (IR), where the readout layer is trained to reconstruct the input time series fed into the ESN. We show that IR can be achieved through unsupervised learning (UL), without access to supervised targets, provided that the ESN parameters are known a priori and satisfy invertibility conditions. This formulation allows applications relying on IR, such as dynamical system replication and noise filtering, to be reformulated within the UL framework via straightforward integration with existing algorithms. Our results suggest that prior knowledge of ESN parameters can reduce reliance on supervision, thereby establishing a new principle—not only by fixing part of the network parameters but also by exploiting their specific values. Furthermore, our UL-based algorithms for input reconstruction and related tasks are suitable for autonomous processing, offering insights into how analogous computational mechanisms might operate in the brain in principle. These findings contribute to a deeper understanding of the mathematical foundations of ESNs and their relevance to models in computational neuroscience.
