Mattia Rigotti

Person

Basel, CH

People

Patents Applicationslast 30 patents

Information Patent Application
GENERATING ANNOTATED DATA SAMPLES FOR TRAINING USING TRAINED GENERA...
- Publication number 20250209796
- Publication date Jun 26, 2025
- International Business Machines Corporation
- Markus POBITZER
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
LAYER NORMALIZATION FOR CALIBRATED UNCERTAINTY IN DEEP LEARNING
- Publication number 20250094784
- Publication date Mar 20, 2025
- International Business Machines Corporation
- Thomas Frick
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
GENERATING STRONG LABELS FOR EXAMPLES LABELLED WITH WEAK LABELS
- Publication number 20240265676
- Publication date Aug 8, 2024
- International Business Machines Corporation
- Klára Janousková
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
GENERATING CAUSAL ASSOCIATION RANKINGS USING DYNAMIC EMBEDDINGS
- Publication number 20240193411
- Publication date Jun 13, 2024
- International Business Machines Corporation
- Jiri Navratil
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
EXPLAINABLE PREDICTION MODELS BASED ON CONCEPTS
- Publication number 20240119276
- Publication date Apr 11, 2024
- International Business Machines Corporation
- MATTIA RIGOTTI
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
NEURAL NETWORKS WITH ANALOG AND DIGITAL MODULES
- Publication number 20220414445
- Publication date Dec 29, 2022
- International Business Machines Corporation
- Malte Johannes Rasch
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
LEVERAGING EXPLANATIONS FOR TRAINING OF AN AI SYSTEM
- Publication number 20220374703
- Publication date Nov 24, 2022
- International Business Machines Corporation
- Mattia Rigotti
- G06 - COMPUTING CALCULATING COUNTING

Mattia Rigotti

Person

Patents Applicationslast 30 patents

GENERATING ANNOTATED DATA SAMPLES FOR TRAINING USING TRAINED GENERA...

LAYER NORMALIZATION FOR CALIBRATED UNCERTAINTY IN DEEP LEARNING

GENERATING STRONG LABELS FOR EXAMPLES LABELLED WITH WEAK LABELS

GENERATING CAUSAL ASSOCIATION RANKINGS USING DYNAMIC EMBEDDINGS

EXPLAINABLE PREDICTION MODELS BASED ON CONCEPTS

NEURAL NETWORKS WITH ANALOG AND DIGITAL MODULES

LEVERAGING EXPLANATIONS FOR TRAINING OF AN AI SYSTEM