Book a demo

Cut patent&paper research from weeks to hours with PatSnap Eureka AI!

Try now

Yoshua Bengio Patents & Innovation Profile — PatSnap Eureka

Yoshua Bengio Patents & Innovation Profile — PatSnap Eureka
Inventor Profile · PatSnap Eureka

Yoshua Bengio: Patent Portfolio & Innovation Analysis

Yoshua Bengio is a Canadian computer scientist and Turing Award laureate who holds 36 patents across 11 jurisdictions, spanning neural network data processing systems, dialect-adaptive speech recognition, and multimodal deep learning architectures, with filings from 1997 to 2021. His portfolio is primarily assigned to Imagia Cybernetics Inc. and reflects a selective but strategically significant engagement with formal IP in two distinct commercial phases — first at AT&T in the late 1990s, then through applied AI ventures from 2017 onward.

36
Patents
1997–2021
Years Active
11
Jurisdictions

Patent Filing Activity

Peak year was 2017 with 10 filings, all through Imagia Cybernetics Inc., followed by 9 filings in 2019 through the Samsung collaboration.

Annual Patent Filings by Yoshua Bengio: 1997=1, 1998=3, 2017=10, 2018=1, 2019=9, 2021=1 Line chart showing Yoshua Bengio's patent filing activity by year, derived from PatSnap Eureka patent database. Peak year was 2017 with 10 filings. 10 7 5 2 0 1997 1998 2017 2018 2019 2021
📋
36
Total Patents
10 active · 13 inactive
📅
1997–2021
Filing Period
Peak activity in 2017
🌐
11
Jurisdictions
US, EP, CA, SG, WO, CN and more
🏢
Imagia Cybernetics
Primary Assignee
11 patents assigned
🔬
G06F15
Top Technology
10 patents in neural network data processing
Patent Analytics

Yoshua Bengio's Patent Filing Patterns

Bengio's filing history shows two distinct phases separated by a 19-year gap: early AT&T filings in 1997–1998, then a concentrated burst of applied AI patents from 2017 onward.

Annual Patent Filings

2017 was the peak year with 10 filings through Imagia Cybernetics, followed by 9 Samsung speech recognition filings in 2019.

Annual Patent Filings by Yoshua Bengio: 1997=1, 1998=3, 2017=10, 2018=1, 2019=9, 2021=1 Line chart showing Yoshua Bengio's patent filing activity by year, derived from PatSnap Eureka patent database. Peak year was 2017 with 10 filings. 10 7 5 2 0 1997 1998 2017 2018 2019 2021

Technology Domain Breakdown

Neural network data processing (G06F15) is the dominant domain with 10 patents, closely followed by speech recognition (G10L15) with 9 patents.

Technology Domain Breakdown for Yoshua Bengio: G06F15=41.7%, G10L15=37.5%, G06N3=8.3%, H04B1=8.3%, G06V30=4.2% Donut chart showing the distribution of Yoshua Bengio's patents across technology domains based on IPC classification codes from PatSnap Eureka. 36 patents G06F15 Neural Processing (41.7%) G10L15 Speech Recognition (37.5%) G06N3 NN Architectures (8.3%) H04B1 Arithmetic Coding (8.3%) G06V30 Doc Recognition (4.2%)

Search Yoshua Bengio's full patent landscape in PatSnap Eureka IP

Explore in PatSnap Eureka IP →
Technology Domains

Yoshua Bengio's Core Areas of Innovation

Bengio's patent portfolio concentrates in neural network data processing and speech recognition, with additional coverage in network architectures, compression, and document recognition.

Neural Network Data Processing Systems

10 patents

This dominant domain covers architectures where neural network modules process structured data including graphs, feature maps, and multimodal inputs. Patents range from the foundational Graph Transformer Network paradigm to modern multimodal processing systems that remain robust when input modalities are missing — a critical challenge in medical imaging and multi-sensor inference.

  • Module for constructing trainable modular network in which each module inputs and outputs data structured as a graph (US6128606A)
  • Method and system for processing a task with robustness to missing input information (WO2017158575A1)
  • Method and system for processing a task with robustness to missing input information (US20190073563A1)
IPC: G06F15

Dialect-Adaptive Speech Recognition

9 patents

This cluster covers a speech recognition architecture co-developed with Samsung Electronics and Université de Montréal. The patents disclose a method for generating dialect-specific parameters from a parameter generation model, applied dynamically to a trained acoustic model to produce a dialect-adapted recogniser — addressing a longstanding robustness problem where monolithic ASR models degrade on non-standard dialects.

  • Speech recognition method and apparatus (US20200126534A1)
  • Speech recognition method and apparatus (EP3640934A1)
  • Device and method for recognising voice, and device and method for training voice recognition model (JP2020067658A)
IPC: G10L15

Neural Network Architectures

2 patents

This subset addresses neural network training procedures and foundational deep learning architecture methods. These patents relate to the theoretical underpinnings of gradient-based learning and network design that informed much of Bengio's subsequent applied work.

  • Neural network training architecture methods
  • Gradient-based learning procedures for modular network systems
IPC: G06N3

Adaptive Binary Arithmetic Coding

2 patents

The Z-coder patents, co-invented with Léon Bottou at AT&T, cover a fast adaptive binary arithmetic coder designed for improved probability estimation and decoding speed. This infrastructure-level compression technology is relevant to signal transmission and data encoding systems, and was developed during Bengio's period at AT&T Bell Labs.

  • Z-coder adaptive binary arithmetic coding system (CA2244380A1)
  • Z-coder adaptive binary arithmetic coding system (CA2244380C)
IPC: H04B1

Document & Pattern Recognition

1 patent

This domain covers the application of trainable modular network architectures to document recognition tasks, including optical character recognition and structured document parsing. The Graph Transformer Network approach introduced in the G06F15 cluster has direct application in document analysis workflows, reflected in this IPC classification.

  • Graph Transformer Network applied to document recognition
  • Modular trainable network for structured document parsing
IPC: G06V30
Most Cited Patents

Yoshua Bengio's Highest-Impact IP

US6128606A leads with 99 forward citations — the 1997 Graph Transformer Network patent co-invented with Léon Bottou and Yann LeCun at AT&T remains the most cited work in the portfolio by a significant margin.

Patent Number Title Year Citations Assignee Status
US6128606A Module for constructing trainable modular network in which each module inputs and outputs data structured as a graph 1997 99 ↑ AT&T Corporation Inactive
WO1998040824A1 Module for constructing trainable modular network in which each module inputs and outputs data structured as a graph 1998 14 ↑ AT&T Corp. Inactive
WO2017158575A1 Method and system for processing a task with robustness to missing input information 2017 12 ↑ Imagia Cybernetics Inc.
US20200126534A1 Speech recognition method and apparatus 2019 12 ↑ Samsung Active
US20190073563A1 Method and system for processing a task with robustness to missing input information 2017 9 ↑ Imagia Cybernetics Inc. Inactive
CN109313627A Method and system for processing a task with robustness to missing input information 2017 3 ↑ 映佳控制公司 Inactive
CA3017697A1 Method and system for processing a task with robustness to missing input information 2017 2 ↑ Imagia Cybernetics Inc. Active
EP3640934A1 Speech recognition method and apparatus 2019 2 ↑ Samsung Active
View the Full Patent Portfolio Analysis
Access complete citation mapping, claim-level analysis, family trees, and legal status tracking for all 36 Bengio patents in PatSnap Eureka IP.
Full family analysis Claim-level search Citation network map Legal status alerts
Analyse in PatSnap Eureka IP →
Collaboration Network

Yoshua Bengio's Research Collaborators

Most Frequent Co-Inventors

Top Co-Inventors of Yoshua Bengio: Nicolas Chapados=11 joint patents, Nicolas Guizard=11 joint patents, Mohammad Havaei=11 joint patents, Yoo Sang Hyun=7 joint patents Horizontal bar chart showing the most frequent co-inventors in Yoshua Bengio's patent portfolio based on PatSnap Eureka data. Chapados 11 Guizard 11 Havaei 11 Yoo Sang Hyun 7

Collaboration Highlights

Bengio's patent collaboration network divides cleanly along the two phases of his filing history. The Imagia Cybernetics cluster is built around a tight four-person team — Nicolas Chapados, Nicolas Guizard, and Mohammad Havaei each appear in 11 joint filings, suggesting a deliberate research and commercialisation partnership in medical imaging AI. The Samsung collaboration introduced a different team led by Yoo Sang Hyun with 7 joint filings, reflecting the co-development agreement between Université de Montréal and Samsung's speech technology division. The early AT&T phase involved Léon Bottou and Yann LeCun, both of whom became equally prominent figures in AI research.

  1. Nicolas Chapados 11 joint patents
  2. Nicolas Guizard 11 joint patents
  3. Mohammad Havaei 11 joint patents
  4. Yoo Sang Hyun 7 joint patents
Map the Full Network in PatSnap Eureka IP
Academic Contributions

Research Literature by Yoshua Bengio

939 papers indexed · Research spans sequence-to-sequence learning, encoder-decoder architectures, neural machine translation, and deep learning fundamentals

Title Year Citations Venue / Source
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation 2014 13,335 ↑ Université de Montréal / Ecole Polytechnique de Montréal
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches 2014 4,952 ↑ Université de Montréal
Graph Attention Networks 2018 2,117 ↑ Université de Montréal / Universitat Politècnica de Catalunya
Practical Recommendations for Gradient-Based Training of Deep Architectures 2012 1,154 ↑ Université de Montréal
On Using Very Large Target Vocabulary for Neural Machine Translation 2015 710 ↑ Université de Montréal

Sequence-to-Sequence Learning & Neural Machine Translation

The largest research cluster covers encoder-decoder architectures and neural machine translation. The 2014 RNN Encoder-Decoder paper (13,335 citations) introduced the foundational architecture for neural translation systems and the attention mechanism era, with direct influence on subsequent transformer-based models.

Speech Recognition & Acoustic Modelling

A substantial body of work covers end-to-end acoustic modelling, convolutional networks for ASR, gated recurrent units, and spoken language understanding — research that directly informed the Samsung speech recognition patents filed from 2018 onward and the dialect-adaptive architecture disclosed in those filings.

Deep Learning Fundamentals & Representation Theory

The third cluster addresses training dynamics, optimisation methods, biologically plausible learning algorithms, and representation theory. The 2012 gradient-based training recommendations paper (1,154 citations) remains a key reference for practitioners designing deep architectures, and constitutes prior art relative to many subsequent patent filings in the field.

Global Footprint

Patent Jurisdictions

Bengio's 36 patents span 11 jurisdictions, with the United States, European Patent Office, and Canada receiving the most filings, reflecting the commercial priorities of AT&T, Imagia Cybernetics, and Samsung.

Patent Jurisdictions for Yoshua Bengio: US=6, EP=4, CA=4, SG=2, WO=2, CN=2, JP=1, KR=1, AT=1, DE=1, HK=1 Horizontal bar chart showing the distribution of Yoshua Bengio's patents by country and jurisdiction based on PatSnap Eureka data. United States 6 Europe (EP) 4 Canada 4 Singapore 2 PCT / WO 2 China 2 Japan 1 South Korea 1 Hong Kong 1 Austria / Germany 1 ea.

Filing Markets

The jurisdictional distribution reflects a commercially rational prosecution strategy: broad US and EP coverage for the core inventions, with selective extension into Asia-Pacific markets where the assignees had active commercial operations or competitive exposure. The Singapore and Hong Kong filings reflect Imagia Cybernetics' multimodal processing family, while Japan and South Korea coverage corresponds to Samsung's home and key export markets for speech technology products.

🇺🇸 United States · 6 🇪🇺 Europe (EP) · 4 🇨🇦 Canada · 4 🇸🇬 Singapore · 2 🌐 PCT / WO · 2 🇨🇳 China · 2 🇯🇵 Japan · 1 🇰🇷 South Korea · 1 🇦🇹 Austria · 1 🇩🇪 Germany · 1 🇭🇰 Hong Kong · 1
For IP Professionals

Why Yoshua Bengio's Portfolio Matters

Strategic implications for patent attorneys, in-house IP teams, and R&D strategists working in AI, speech technology, and medical imaging.

⚠️

FTO Considerations

The multimodal feature map processing family — centred on the "robustness to missing input information" architecture — covers a design pattern with broad applicability in medical AI, autonomous systems, and multi-sensor applications where input dropout is a realistic operating condition. Several family members expired in 2024–2025, entering the public domain. However, active family members in the US and Canada (including CA3017697C, granted January 2021) remain live, and claim scope should be assessed carefully before designing around this architecture. The Samsung speech recognition family is fully active across US, EP, CN, JP, and KR, and covers a dialect-parameter generation approach that any commercial ASR developer working on accent or dialect adaptation should review.

🔍

Prior Art Relevance

Bengio's academic record is arguably more significant than the patent portfolio for anyone filing in deep learning-adjacent domains. His 2014 publications on encoder-decoder architectures and the broader body of work on recurrent networks, attention mechanisms, and sequence modelling — including the RNN Encoder-Decoder paper with 13,335 citations — form a dense layer of prior art that predates many subsequent patent applications by other filers. IP teams conducting patentability assessments in NLP, speech, or sequence learning should include Bengio's 939-paper academic output — not just his patents — in their search strategy. The patents appear to formalise specific implementations of concepts validated through prior academic publication, making publication dates critical for prior art dating.

Unlock Licensing & Monitoring Insights
Access full FTO analysis, licensing opportunity mapping, and portfolio monitoring for Yoshua Bengio's IP in PatSnap Eureka.
Licensing opportunities Monitoring alerts Full FTO report
Access in PatSnap Eureka IP →
Frequently Asked Questions

Yoshua Bengio Patent Portfolio — Common Questions

Yoshua Bengio holds 36 patent records across 11 jurisdictions, spanning 20 unique base inventions filed between 1997 and 2021. Of these, 10 are currently active, 13 are inactive, and the primary assignee is Imagia Cybernetics Inc. with 11 records.
Bengio's patent activity concentrates in two areas: neural network data processing systems — specifically graph-structured network architectures and multimodal processing with robustness to missing inputs (IPC G06F15, 10 patents) — and dialect-adaptive automatic speech recognition (IPC G10L15, 9 patents). An earlier filing covers adaptive binary arithmetic coding (H04B1, 2 patents), and a smaller subset addresses neural network architectures (G06N3, 2 patents).
The primary assignee is Imagia Cybernetics Inc., which holds 11 records covering the multimodal processing family. Samsung Electronics and Université de Montréal are joint assignees on the speech recognition family (9 records). The earliest patents, from 1997–1998, were assigned to AT&T Corporation and cover the Graph Transformer Network and Z-coder arithmetic coding inventions.
Nicolas Chapados, Nicolas Guizard, and Mohammad Havaei each appear in 11 joint filings, all within the Imagia Cybernetics portfolio covering multimodal neural network processing. Yoo Sang Hyun appears in 7 joint filings through the Samsung speech recognition collaboration. The early AT&T filings (1997–1998) were co-invented with Léon Bottou and Yann LeCun.
US6128606A — Module for constructing trainable modular network in which each module inputs and outputs data structured as a graph — filed in 1997 and assigned to AT&T Corporation, with 99 forward citations. It introduced the Graph Transformer Network framework, co-invented with Léon Bottou and Yann LeCun, and its forward citation trail runs through document classification, optical character recognition, and graph neural network literature.
The relationship is sequential rather than parallel. Bengio typically published research concepts academically before any related patent filings, meaning his 939 academic papers — including the 2014 RNN Encoder-Decoder paper with 13,335 citations — frequently constitute prior art relative to subsequent third-party patents in the same domains. The Imagia Cybernetics and Samsung patents both have clear antecedents in his published research on deep architectures, multimodal learning, and adaptive speech modelling, making his publication record an essential component of any thorough prior art search in these fields.

Analyse Yoshua Bengio's Full Patent Portfolio

Access citation mapping, claim-level search, FTO analysis, and inventor network intelligence across all 36 patents and 939 papers in PatSnap Eureka IP.

References & External Sources

PatSnap Eureka IP
208M+ patents & papers · AI-powered search
Ask anything about Yoshua Bengio's patents.
PatSnap Eureka searches 208M+ patents and papers to answer instantly.
Try asking