@prefix rdf:   <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix sl:    <http://www.semanlink.net/2001/00/semanlink-schema#> .
@prefix skos:  <http://www.w3.org/2004/02/skos/core#> .
@prefix rdfs:  <http://www.w3.org/2000/01/rdf-schema#> .
@prefix tag:   <http://www.semanlink.net/tag/> .
@prefix foaf:  <http://xmlns.com/foaf/0.1/> .
@prefix dc:    <http://purl.org/dc/elements/1.1/> .

tag:antoine_bordes  a   sl:Tag ;
        skos:prefLabel  "Antoine Bordes" .

tag:consciousness_prior
        a               sl:Tag ;
        skos:broader    tag:yoshua_bengio ;
        skos:prefLabel  "Consciousness Prior" .

<http://www.semanlink.net/doc/2025/10/un_pionnier_de_l%E2%80%99ia_veut_constr>
        dc:title         "Un pionnier de l’IA veut construire des systèmes non nuisibles à l’humanité" ;
        sl:creationDate  "2025-10-28" ;
        sl:tag           tag:yoshua_bengio .

<http://www.semanlink.net/doc/2023/04/yoshua_bengio_se_joint_aux_cent>
        dc:title         "Yoshua Bengio se joint aux centaines de signataires d'une lettre ouverte plaidant pour des systèmes d'IA plus sûrs - Mila" ;
        sl:creationDate  "2023-04-05" ;
        sl:tag           tag:yoshua_bengio , tag:pause_giant_ai_experiments .

<http://www.iro.umontreal.ca/~bengioy/talks/MIT-18oct2018.pdf>
        dc:title         "Towards bridging the gap between deep learning and brains" ;
        sl:comment       "> Underlying Assumption: There are principles giving rise to intelligence (machine, human\r\nor animal) via learning, simple enough that they can be\r\ndescribed compactly, similarly to the laws of physics, i.e., our\r\nintelligence is not just the result of a huge bag of tricks and\r\npieces of knowledge, but of general mechanisms to acquire\r\nknowledge." ;
        sl:creationDate  "2018-10-23" ;
        sl:tag           tag:yoshua_bengio , tag:slides , tag:brain_vs_deep_learning .

tag:backpropagation_vs_biology
        a               sl:Tag ;
        skos:prefLabel  "Backpropagation vs Biology" .

tag:ronan_collobert  a  sl:Tag ;
        skos:prefLabel  "Ronan Collobert" .

tag:grand_homme  a      sl:Tag ;
        skos:prefLabel  "Grand Homme" .

<http://www.semanlink.net/doc/2025/06/questions_frequentes_sur_les_ri>
        dc:title         "Questions fréquentes sur les risques catastrophiques liés à l’IA - Yoshua Bengio" ;
        sl:creationDate  "2025-06-01" ;
        sl:tag           tag:yoshua_bengio , tag:ai_dangers .

tag:yoshua_bengio  a      sl:Tag ;
        rdfs:isDefinedBy  tag:yoshua_bengio.n3 ;
        sl:comment        "> la question cruciale est donc de savoir comment apprendre à comprendre. ([src](https://yoshuabengio.org/fr/recherche/))" ;
        skos:broader      tag:ai_girls_and_guys , tag:grand_homme , tag:nlp_girls_and_guys ;
        skos:prefLabel    "Yoshua Bengio" ;
        skos:related      tag:generative_adversarial_network , tag:autoencoder , tag:samy_bengio , tag:word_embedding ;
        foaf:page         tag:yoshua_bengio.html .

tag:time_series  a      sl:Tag ;
        skos:prefLabel  "Time Series" .

tag:thought_vector  a   sl:Tag ;
        skos:prefLabel  "Thought Vector" .

tag:ai_science_and_society_conf_2025
        a               sl:Tag ;
        skos:prefLabel  "AI, Science and Society (conf 2025)" .

tag:word_embedding  a   sl:Tag ;
        skos:prefLabel  "Word embeddings" .

tag:yuval_noah_harari
        a               sl:Tag ;
        skos:prefLabel  "Yuval Noah Harari" .

tag:combinatorial_optimization
        a               sl:Tag ;
        skos:prefLabel  "Combinatorial optimization" .

tag:ai_dangers  a       sl:Tag ;
        skos:prefLabel  "AI: dangers" .

tag:hierarchical_memory_networks
        a               sl:Tag ;
        skos:prefLabel  "Hierarchical Memory Networks" .

<http://www.semanlink.net/doc/2025/02/yoshua_bengio_ia_%C2%ABdes_prises>
        dc:title         "Yoshua Bengio (IA): «Des prises de risques dangereuses vont s’accentuer à mesure qu'elle va progresser» - RFI" ;
        sl:creationDate  "2025-02-08" ;
        sl:tag           tag:yoshua_bengio , tag:ai_dangers , tag:ai_science_and_society_conf_2025 .

tag:deep_learning  a    sl:Tag ;
        skos:prefLabel  "Deep Learning" .

tag:autoencoder  a      sl:Tag ;
        skos:prefLabel  "Autoencoder" .

tag:deep_learning_attention
        a               sl:Tag ;
        skos:prefLabel  "Attention mechanism" .

tag:slides  a           sl:Tag ;
        skos:prefLabel  "Slides" .

<https://www.youtube.com/watch?v=Yr1mOzC93xs>
        dc:title         "From Deep Learning of Disentangled Representations to Higher-level Cognition - YouTube" ;
        sl:comment       "> **What's wrong with our unsupervised training objectives ? They are in pixel space rather than in abstract space**\r\n\r\n> Many more entropy bits in acoustics details than linguistic content.\r\n\r\nRelated to [this paper](/doc/?uri=https%3A%2F%2Farxiv.org%2Fabs%2F1709.08568)" ;
        sl:creationDate  "2018-09-28" ;
        sl:tag           tag:youtube_video , tag:yoshua_bengio , tag:human_level_ai , tag:deep_learning , tag:consciousness_prior .

tag:yann_lecun  a       sl:Tag ;
        skos:prefLabel  "Yann LeCun" .

tag:pause_giant_ai_experiments
        a               sl:Tag ;
        skos:prefLabel  "Pause Giant AI Experiments" .

tag:brain_vs_deep_learning
        a               sl:Tag ;
        skos:prefLabel  "Brain vs Deep Learning" .

tag:machine_learning  a  sl:Tag ;
        skos:prefLabel  "Machine learning" .

<http://www.deeplearningbook.org/>
        dc:title         "Deep Learning (Ian Goodfellow and Yoshua Bengio and Aaron Courville)" ;
        sl:creationDate  "2017-12-16" ;
        sl:tag           tag:yoshua_bengio , tag:ian_goodfellow , tag:deep_learning_book .

<https://arxiv.org/abs/1605.07427>
        dc:title         "[1605.07427] Hierarchical Memory Networks" ;
        sl:comment       "> hybrid between hard and soft attention memory networks. The memory is organized in a hierarchical structure such that reading from it is done with less computation than soft attention over a flat memory, while also being easier to train than hard attention over a flat memory" ;
        sl:creationDate  "2018-11-14" ;
        sl:tag           tag:yoshua_bengio , tag:hierarchical_memory_networks , tag:arxiv_doc .

tag:arxiv_doc  a        sl:Tag ;
        skos:prefLabel  "Arxiv Doc" .

tag:restricted_boltzmann_machine
        a               sl:Tag ;
        skos:prefLabel  "Restricted Boltzmann machine" .

tag:computational_neuroscience
        a               sl:Tag ;
        skos:prefLabel  "Computational Neuroscience" .

tag:nn_symbolic_ai_hybridation
        a               sl:Tag ;
        skos:prefLabel  "http://www.semanlink.net/tag/nn_symbolic_ai_hybridation" .

<https://www.quora.com/How-does-one-apply-deep-learning-to-time-series-forecasting>
        dc:title         "How does one apply deep learning to time series forecasting? - Quora" ;
        sl:comment       "> I would use the state-of-the-art [recurrent nets](/tag/recurrent_neural_network.html) (using gated units and multiple layers) to make predictions at each time step for some future horizon of interest. The RNN is then updated with the next observation to be ready for making the next prediction" ;
        sl:creationDate  "2017-10-22" ;
        sl:tag           tag:yoshua_bengio , tag:time_series , tag:recurrent_neural_network .

<http://www.semanlink.net/doc/2019/08/learning_structured_embeddings_>
        dc:title         "Learning Structured Embeddings of Knowledge Bases (2011)" ;
        sl:creationDate  "2019-08-03" ;
        sl:tag           tag:yoshua_bengio , tag:ronan_collobert , tag:knowledge_graph_embeddings , tag:antoine_bordes .

tag:word_embeddings_with_lexical_resources
        a               sl:Tag ;
        skos:prefLabel  "Word embeddings with lexical resources" .

<https://arxiv.org/abs/1709.08568>
        dc:title         "[1709.08568] The Consciousness Prior" ;
        sl:comment       "\"consciousness seen as the formation of a low-dimensional combination of a few concepts constituting a conscious thought, i.e., **consciousness as awareness at a particular time instant**\": the projection of a big vector (all the things conscious and unconscious in brain). Attention: additional mechanism describing what mind chooses to focus on.\r\n\r\n[YouTube video](/doc/?uri=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DYr1mOzC93xs)" ;
        sl:creationDate  "2017-09-29" ;
        sl:tag           tag:thought_vector , tag:deep_learning_attention , tag:good , tag:arxiv_doc , tag:representation_learning , tag:consciousness_prior , tag:human_level_ai , tag:conscience_artificielle , tag:yoshua_bengio .

tag:geoffrey_hinton  a  sl:Tag ;
        skos:prefLabel  "Geoffrey Hinton" .

tag:human_level_ai  a   sl:Tag ;
        skos:prefLabel  "Human Level AI" .

<https://openreview.net/forum?id=rJXMpikCZ>
        dc:title         "Graph Attention Networks (2018)" ;
        sl:comment       "A novel approach to processing graph-structured data by neural networks, leveraging **masked self-attentional layers over a node's neighborhood**. (-> different weights to different nodes in a neighborhood, without requiring any kind of computationally intensive matrix operation or depending on knowing the graph structure upfront)." ;
        sl:creationDate  "2018-11-14" ;
        sl:tag           tag:yoshua_bengio , tag:attention_in_graphs .

tag:artificial_intelligence
        a               sl:Tag ;
        skos:prefLabel  "Artificial Intelligence" .

<http://www.semanlink.net/doc/2021/07/2102_11107_towards_causal_rep>
        dc:title         "[2102.11107] Towards Causal Representation Learning" ;
        sl:comment       "This article reviews fundamental concepts of causal inference and relates them to crucial open problems of machine learning, including transfer learning and generalization, thereby assaying how causality can contribute to modern machine learning research\r\n\r\nRelated: [Making sense of raw input](doc:2021/05/making_sense_of_raw_input)" ;
        sl:creationDate  "2021-07-15" ;
        sl:tag           tag:yoshua_bengio , tag:machine_learning , tag:causal_inference , tag:arxiv_doc .

tag:ai_girls_and_guys
        a               sl:Tag ;
        skos:prefLabel  "AI girls and guys" .

tag:samy_bengio  a      sl:Tag ;
        skos:prefLabel  "Samy Bengio" .

tag:good  a             sl:Tag ;
        skos:prefLabel  "Good" .

<http://www.semanlink.net/doc/2021/03/equilibrium_propagation_bridgi>
        dc:title         "Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation | Frontiers in Computational Neuroscience" ;
        sl:creationDate  "2021-03-19" ;
        sl:tag           tag:yoshua_bengio , tag:computational_neuroscience , tag:backpropagation_vs_biology .

tag:meaning_in_nlp  a   sl:Tag ;
        skos:prefLabel  "Meaning in NLP" .

<http://www.semanlink.net/doc/2019/10/feature_wise_transformations>
        dc:title         "Feature-wise transformations. A simple and surprisingly effective family of conditioning mechanisms. (2018)" ;
        sl:comment       "> Many real-world problems require integrating multiple sources of information...When approaching such problems, it often makes sense to process one source of information in the context of another. In machine learning, we often refer to this context-based processing as conditioning: the computation carried out by a model is **conditioned** or **modulated** by information extracted from an auxiliary input. Eg.: **extract meaning from the image in the context of the question**.\r\n\r\nRelated to this talk at Paris NLP meetup:  [\"Language and Perception in Deep Learning\"](/doc/2019/10/language_and_perception_in_deep)" ;
        sl:creationDate  "2019-10-07" ;
        sl:tag           tag:yoshua_bengio , tag:ml_conditioning , tag:grounded_language_learning .

tag:causal_inference  a  sl:Tag ;
        skos:prefLabel  "Causal inference" .

tag:nlp_girls_and_guys
        a               sl:Tag ;
        skos:prefLabel  "NLP girls and guys" .

tag:recurrent_neural_network
        a               sl:Tag ;
        skos:prefLabel  "Recurrent neural network" .

<https://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf>
        dc:title         "Learning Deep Architectures for AI By Yoshua Bengio (2009)" ;
        sl:creationDate  "2018-11-06" ;
        sl:tag           tag:yoshua_bengio , tag:good , tag:deep_learning .

<http://www.semanlink.net/doc/2023/04/yoshua_bengio_chercheur_%C2%AB_au>
        dc:title         "Yoshua Bengio, chercheur : « Aujourd’hui, l’intelligence artificielle, c’est le Far West ! Nous devons ralentir et réguler »" ;
        sl:comment       "Interviews concomitantes de Bengio et [LeCun](doc:2023/04/yann_le_cun_directeur_a_meta_) par le Monde\r\n\r\n> il n’est pas impossible\r\nque l’on parvienne à fabriquer un jour ce qui pourrait\r\nressembler aux mécanismes de la [conscience](tag:conscience_artificielle)\r\n\r\n> On ne peut pas continuer avec des décisions qui, alors\r\nqu’elles touchent autant la société, sont laissées aux\r\nseules entreprises qui ont les moyens de développer ces\r\noutils" ;
        sl:creationDate  "2023-04-29" ;
        sl:tag           tag:yoshua_bengio , tag:pause_giant_ai_experiments , tag:artificial_intelligence .

<https://www.quora.com/How-do-RBMs-work-What-are-some-good-use-cases-and-some-good-recent-papers-on-the-topic>
        dc:title         "How do RBMs work? - Quora" ;
        sl:comment       "> You can think of it a little bit like you think about Principal Components Analysis, in that it is trained by unsupervised learning so as to capture the leading variations in the data, and it yields a new representation of the data" ;
        sl:creationDate  "2017-10-30" ;
        sl:tag           tag:yoshua_bengio , tag:restricted_boltzmann_machine .

<http://www.semanlink.net/doc/2021/08/deep_learning_for_ai_%7C_july_202>
        dc:title         "Deep Learning for AI | July 2021 | Communications of the ACM" ;
        sl:creationDate  "2021-08-02" ;
        sl:tag           tag:yoshua_bengio , tag:yann_lecun , tag:nn_symbolic_ai_hybridation , tag:geoffrey_hinton , tag:deep_learning , tag:artificial_intelligence .

tag:grounded_language_learning
        a               sl:Tag ;
        skos:prefLabel  "Grounded Language Learning" .

<http://aclweb.org/anthology/Q16-1002>
        dc:title         "Learning to Understand Phrases by Embedding the Dictionary (2016)" ;
        sl:comment       "> The composed meaning of the words in a dictionary definition (a tall, long-necked, spotted ruminant of Africa) should correspond to the meaning of the word they define (giraffe)" ;
        sl:creationDate  "2018-08-23" ;
        sl:tag           tag:yoshua_bengio , tag:word_embeddings_with_lexical_resources .

tag:attention_in_graphs
        a               sl:Tag ;
        skos:prefLabel  "Attention in Graphs" .

<http://www.semanlink.net/doc/2019/09/what_s_next_for_ai_yoshua_ben>
        dc:title         "What's next for AI - Yoshua Bengio (Interview)" ;
        sl:creationDate  "2019-09-17" ;
        sl:tag           tag:yoshua_bengio .

tag:deep_learning_book
        a               sl:Tag ;
        skos:prefLabel  "Deep Learning Book" .

<http://www.semanlink.net/doc/2020/04/2004_10151_experience_grounds>
        dc:title         "[2004.10151] Experience Grounds Language" ;
        sl:creationDate  "2020-04-22" ;
        sl:tag           tag:yoshua_bengio , tag:survey , tag:meaning_in_nlp , tag:grounded_language_learning , tag:arxiv_doc .

tag:conscience_artificielle
        a               sl:Tag ;
        skos:prefLabel  "Conscience artificielle" .

tag:survey  a           sl:Tag ;
        skos:prefLabel  "Survey / Review" .

tag:ian_goodfellow  a   sl:Tag ;
        skos:prefLabel  "Ian Goodfellow" .

tag:ml_conditioning  a  sl:Tag ;
        skos:prefLabel  "ML: conditioning" .

<http://www.semanlink.net/doc/2019/12/yoshua_bengio_revered_architec>
        dc:title         "Yoshua Bengio, Revered Architect of AI, Has Some Ideas About What to Build Next - IEEE Spectrum" ;
        sl:creationDate  "2019-12-18" ;
        sl:tag           tag:yoshua_bengio .

<http://www.semanlink.net/doc/2022/12/machine_learning_for_combinator>
        dc:title         "Machine learning for combinatorial optimization: A methodological tour d’horizon" ;
        sl:creationDate  "2022-12-09" ;
        sl:tag           tag:yoshua_bengio , tag:survey , tag:machine_learning , tag:combinatorial_optimization .

<http://www.semanlink.net/doc/2020/02/yoshua_bengio>
        dc:title         "Yoshua Bengio" ;
        sl:comment       "[Yoshua Bengio’s blog – first words](https://yoshuabengio.org/2020/02/10/fusce-risus/)" ;
        sl:creationDate  "2020-02-12" ;
        sl:tag           tag:yoshua_bengio .

tag:representation_learning
        a               sl:Tag ;
        skos:prefLabel  "Representation learning" .

tag:generative_adversarial_network
        a               sl:Tag ;
        skos:prefLabel  "GAN" .

tag:youtube_video  a    sl:Tag ;
        skos:prefLabel  "YouTube video" .

<http://www.deeplearningbook.org/contents/representation.html>
        dc:title         "Representation learning (in \"Deep Learning\", Ian Goodfellow and Yoshua Bengio and Aaron Courville)" ;
        sl:creationDate  "2017-12-16" ;
        sl:tag           tag:yoshua_bengio , tag:representation_learning , tag:ian_goodfellow .

tag:knowledge_graph_embeddings
        a               sl:Tag ;
        skos:prefLabel  "Knowledge Graph Embeddings" .

<http://www.semanlink.net/doc/2025/06/comment_des_ia_nocives_pourraie>
        dc:title         "Comment des IA nocives pourraient apparaître - Yoshua Bengio" ;
        sl:creationDate  "2025-06-01" ;
        sl:tag           tag:yuval_noah_harari , tag:yoshua_bengio , tag:ai_dangers .