Ryo Karakida

428 total citations
22 papers, 159 citations indexed

About

Ryo Karakida is a scholar working on Artificial Intelligence, Statistical and Nonlinear Physics and Computer Vision and Pattern Recognition. According to data from OpenAlex, Ryo Karakida has authored 22 papers receiving a total of 159 indexed citations (citations by other indexed papers that have themselves been cited), including 17 papers in Artificial Intelligence, 7 papers in Statistical and Nonlinear Physics and 6 papers in Computer Vision and Pattern Recognition. Recurrent topics in Ryo Karakida's work include Neural Networks and Applications (11 papers), Gaussian Processes and Bayesian Inference (5 papers) and Machine Learning and ELM (4 papers). Ryo Karakida is often cited by papers focused on Neural Networks and Applications (11 papers), Gaussian Processes and Bayesian Inference (5 papers) and Machine Learning and ELM (4 papers). Ryo Karakida collaborates with scholars based in Japan and France. Ryo Karakida's co-authors include Шун-ичи Амари, Masafumi Oizumi, Masato Okada, Masato Okada, Hideki Asoh, Shotaro Akaho, Kazuki Osawa, Tomoko Ozeki, Marco Cuturi and Takayuki Hoshino and has published in prestigious journals such as Scientific Reports, Expert Systems with Applications and Neural Computation.

In The Last Decade

Ryo Karakida

17 papers receiving 156 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Ryo Karakida Japan	8	68	38	37	25	18	22	159
Boris Hanin United States	5	56 0.8×	29 0.8×	27 0.7×	9 0.4×	23 1.3×	9	159
Vitaly Maiorov Israel	7	135 2.0×	35 0.9×	44 1.2×	23 0.9×	16 0.9×	9	232
Stephan Wojtowytsch United States	5	58 0.9×	41 1.1×	19 0.5×	8 0.3×	6 0.3×	10	119
Alessandro Rudi Italy	8	73 1.1×	13 0.3×	44 1.2×	16 0.6×	24 1.3×	24	167
Alex Zhai United States	6	165 2.4×	5 0.1×	161 4.4×	19 0.8×	28 1.6×	10	289
J. Y. Shi United States	6	68 1.0×	26 0.7×	30 0.8×	13 0.5×		17	124
Nadir Murru Italy	8	54 0.8×	17 0.4×	32 0.9×	6 0.2×	9 0.5×	45	183
Markus Maier Germany	4	112 1.6×	35 0.9×	87 2.4×	2 0.1×	10 0.6×	4	186
Vassilis Kalofolias Switzerland	5	113 1.7×	54 1.4×	72 1.9×	2 0.1×	7 0.4×	6	207
Rémi Bardenet France	6	125 1.8×	13 0.3×	24 0.6×	2 0.1×	16 0.9×	15	308

Countries citing papers authored by Ryo Karakida

Since Specialization

Citations

This map shows the geographic impact of Ryo Karakida's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Ryo Karakida with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Ryo Karakida more than expected).

Fields of papers citing papers by Ryo Karakida

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Ryo Karakida. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Ryo Karakida. The network helps show where Ryo Karakida may publish in the future.

Co-authorship network of co-authors of Ryo Karakida

This figure shows the co-authorship network connecting the top 25 collaborators of Ryo Karakida. A scholar is included among the top collaborators of Ryo Karakida based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Ryo Karakida. Ryo Karakida is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Kanoga, Suguru, et al.. (2025). Continual learning in inertial measurement unit-based human activity recognition with user-centric class-incremental learning scenario. Expert Systems with Applications. 280. 127469–127469.

Karakida, Ryo, et al.. (2025). Modeling natural neural networks of decision making with artificial neural networks. Neuroscience Research. 220. 104961–104961.

Karakida, Ryo. (2024). Universal Laws of Learning Emerging in Wide Neural Networks and Their Current State. 31(4). 167–176.

Karakida, Ryo, et al.. (2024). Optimal layer selection for latent data augmentation. Neural Networks. 181. 106753–106753.

Kanoga, Suguru, et al.. (2024). Deep Generative Replay-based Class-incremental Continual Learning in sEMG-based Pattern Recognition. PubMed. 2024. 1–4.

Sakamoto, Kotaro, et al.. (2023). Deep learning in random neural fields: Numerical experiments via neural tangent kernel. Neural Networks. 160. 148–163. 1 indexed citations

Karakida, Ryo, et al.. (2023). Attention in a Family of Boltzmann Machines Emerging From Modern Hopfield Networks. Neural Computation. 35(8). 1463–1480. 4 indexed citations

Karakida, Ryo, Shotaro Akaho, & Шун-ичи Амари. (2021). Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks. Neural Computation. 33(8). 2274–2307. 5 indexed citations

Karakida, Ryo, et al.. (2021). Self-paced data augmentation for training neural networks. Neurocomputing. 442. 296–306. 14 indexed citations

10.

Karakida, Ryo, Shotaro Akaho, & Шун-ичи Амари. (2020). Universal statistics of Fisher information in deep neural networks: mean field approach ^*. Journal of Statistical Mechanics Theory and Experiment. 2020(12). 124005–124005. 7 indexed citations

11.

Karakida, Ryo, et al.. (2020). Collective dynamics of repeated inference in variational autoencoder rapidly find cluster structure. Scientific Reports. 10(1). 16001–16001. 2 indexed citations

12.

Karakida, Ryo & Kazuki Osawa. (2020). Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. arXiv (Cornell University). 7 indexed citations

13.

Амари, Шун-ичи, Ryo Karakida, & Masafumi Oizumi. (2019). Statistical neurodynamics of deep networks: geometry of signal spaces. Nonlinear Theory and Its Applications IEICE. 10(4). 322–336. 2 indexed citations

14.

Karakida, Ryo, Shotaro Akaho, & Шун-ичи Амари. (2018). Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach. International Conference on Artificial Intelligence and Statistics. 1032–1041. 1 indexed citations

15.

Амари, Шун-ичи, Ryo Karakida, & Masafumi Oizumi. (2018). Information geometry connecting Wasserstein distance and Kullback–Leibler divergence via the entropy-relaxed transportation problem. 1(1). 13–37. 43 indexed citations

16.

Karakida, Ryo, et al.. (2017). Statistical Mechanical Analysis of Online Learning with Weight Normalization in Single Layer Perceptron. Journal of the Physical Society of Japan. 86(4). 44002–44002. 7 indexed citations

17.

Амари, Шун-ичи, et al.. (2017). Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited. Neural Computation. 30(1). 1–33. 20 indexed citations

18.

Karakida, Ryo, Masato Okada, & Шун-ичи Амари. (2016). Maximum likelihood learning of RBMs with Gaussian visible units on the Stiefel manifold.. The European Symposium on Artificial Neural Networks. 1 indexed citations

19.

Karakida, Ryo, Masato Okada, & Шун-ичи Амари. (2016). Dynamical analysis of contrastive divergence learning: Restricted Boltzmann machines with Gaussian visible units. Neural Networks. 79. 78–87. 29 indexed citations

20.

Karakida, Ryo, Masato Okada, & Шун-ичи Амари. (2016). Adaptive Natural Gradient Learning Based on Riemannian Metric of Score Matching. 1 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact