Daniel Saromo-Mori

Daniel
Saromo-Mori

Mechatronic Engineer

Inventor of Auto-Rotating Neural Networks

AI Researcher & Lecturer

Entrepreneur

NOTE: This website is still under renovation!

200+
Citations
11
Countries
6+
Years Teaching
4
Languages
Scroll

What makes him unique

The Invention

x₁ x₂ x₃ ARP ARP ŷ Input Auto-Rotating Output

Auto-Rotating Neural Networks

"When using deep neural networks, do we ever change the neuron itself?"

The Auto-Rotating Perceptron (ARP) introduces a novel activation mechanism that rotates in the weight space, tackling the vanishing gradient problem from a fundamentally different angle. This concept has been extended, becoming the Auto-Rotating Neural Network (ARNN) family.

  • Novel activation mechanism that rotates in weight space
  • Tackles vanishing gradient problem
  • Open-source Keras library (arpkeras)
  • Under review at TMLR (Transactions on Machine Learning Research)

Presented at

LXAI NeurIPS 2019 LXAI ICML 2020 OAMLS ACML 2021
Open-source ARP Library

11 Countries, 16 Institutions

Professional Journey

2014 B.Sc. Mechatronics Engineering

Lima, Peru

PUCP University

2014-2020

  • Pontifical Catholic University of Peru (PUCP): #1 in Peru (QS Ranking 2025).
  • Ranked at the top 6.66% of the Faculty of Science and Engineering.
  • Ranked 5th of 32 graduates of the Mechatronics Engineering cohort 2019.
  • Thesis: Spider robot thesis for landmine detection.
  • Professional Degree (Ing.) obtained at 2020.
2019 Travel Award for IMECE 2019

Utah, USA

ASME

November 9, 2019

  • Representing South America at ASME IMECE 2019
2019 Research Paper + Oral Presenter

Vancouver, Canada

LXAI NeurIPS

December 8-14, 2019

  • Presenting the paper “Auto-Rotating Perceptrons” in the LXAI workshop as an oral exposition and poster presentation.
2020 Guest Researcher

Bremen, Germany *

DFKI

2020

  • Extended ARP → ARNN family.
  • DFKI: German Research Center for AI.
  • Held virtually due to the global COVID-19 situation.
2020 Research Paper + Oral Presenter

Vienna, Austria *

LXAI ICML

July 12-18, 2020

  • Presenting the paper “Smart Sensor Calibration with Auto-Rotating Perceptrons” in the LXAI workshop as an oral exposition and poster presentation.
  • Held virtually due to the global COVID-19 situation.
2021 Oral Presenter

Guatemala, Guatemala *

PWLG

March 22, 2021

  • I gave a tutorial about the Auto-Rotating Perceptrons for the group Papers We Love Guatemala.
  • In this talk, I taught how to use the ARP by presenting the Keras ARP Library and a example notebook.
  • Held virtually due to the global COVID-19 situation.
2021 Summer School + Oral Presenter

Singapore, Singapore *

OAMLS at ACML

November 8-19, 2021

  • Attended the Asian Conference in Machine Learning (ACML) 2021.
  • Presenting the poster “Auto-Rotating Neural Networks” in the Online Asian Machine Learning School (OAMLS).
  • Held virtually due to the global COVID-19 situation.
2022 Research Paper + Oral Presenter

Louisiana, USA

LXAI CVPR

June 19-21, 2022

  • Presenting the paper “A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement” in the LXCV workshop as an oral exposition and poster presentation.
2022 Research Paper at Conference

Warsaw, Poland

9th Int. Symposium on Sensor Science

August 31, 2022

  • Publication of the paper Smart Insole Sensor for vGRF Measurement.
  • Paper published at the 9th International Symposium on Sensor Science at Warsaw, Poland.
  • Link: https://www.mdpi.com/2673-4591/21/1/47.
2022 M.Sc. (c) Automation & Control

Milan, Italy

Politecnico Di Milano

2022-2024

  • PoliMi: #13 worldwide (QS Ranking 2022).
  • Weighted grade after 3 semesters: 25.6/30.
  • 1st place at Pitch Competition 2023.
2024 M.Sc. Cybernetics & Robotics

Prague, Czechia

Czech Technical University

Since 2024

  • CTU: #1 in Czechia (QS Ranking 2025).
2024 Oral Presenter

Prague, Czechia

PRG.AI + CIIRC

October 16, 2024

  • Dny AI: AI-focused series of events taking place across Czechia.
  • I presented the pitch “Auto-Rotating Neural Networks” in the DNY AI Workshop as an oral exposition and poster presentation (Link: https://www.youtube.com/watch?v=8U1lcTAYTZY, Timestamp: 1:12:00).
  • Oral presentation given at the CIIRC conferene room: Czech Institute of Informatics, Robotics and Cybernetics.
2025 Summer School

Malmo, Sweden

GameAI Summer School

June 23-27, 2025

  • 7th International Summer School of AI and Games (Malmö Edition).
2025 Summer School

Potsdam, Germany

Hasso-Plattner-Institut (HPI)

September 8-12, 2025

  • Summer School (on-site): How to be a (Startup-) CTO
  • M.Sc. credits awarded: 3 ECTS
2025 Internship

Prague, Czechia

Siemens

Since 2025

  • Internship: IT/OT Integration.
  • Master Thesis done at Siemens.
2026 Specialization in AI

Prague, Czechia

Charles University

2026

  • Exchange semester done as part of the AI Specialization: PRG.AI minor.

Academic output

Publications

200+ Citations
CVPR 2022 200 cites

A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement

Workshop Oral + Poster New Orleans
Sensor Science 2022

Smart Insole Sensor for vGRF Measurement Using ARP

Conference Paper Warsaw
ICML 2020

Smart Sensor Calibration with Auto-Rotating Perceptrons

Workshop Oral + Poster Vienna
NeurIPS 2019 1 cites

Auto-Rotating Perceptrons

Workshop Oral + Poster Vancouver
PUCP Thesis 2020 1 cites

Intelligent Spider Robot for Detecting Anti-Personnel Metallic Landmines

BSc + Professional Thesis Lima
View on Google Scholar

Sharing knowledge

Teaching

6+ Years | 24+ Semesters
12
semesters

AI for Games

PUCP

7
semesters

ML for Industry

CETAM-PUCP

5
semesters

Python for Data Science

CETAM-PUCP

1
semesters

Data Analysis & Time Series

PUCP

Also:
SENAMHI (AI/ML Lecturer, 2022) EsSalud (ML Lecturer, 2022)

Teaching Assistant at PUCP for AI, ML, and CS Applications (2019)

Get in touch

Contact

danielsaromo [at] gmail [dot] com
LinkedIn GitHub Scholar ORCID Instagram
danielsaromo.xyz

Daniel Saromo-Mori · Prague, Czechia