http://www.semanlink.net/tag/yoshua_bengio Documents tagged with Yoshua Bengio http://www.semanlink.net/doc/2025/10/un_pionnier_de_l%E2%80%99ia_veut_constr 2025-10-28T19:07:37Z http://www.semanlink.net/doc/2025/06/comment_des_ia_nocives_pourraie 2025-06-01T02:15:55Z http://www.semanlink.net/doc/2025/06/questions_frequentes_sur_les_ri 2025-06-01T01:56:20Z http://www.semanlink.net/doc/2025/02/yoshua_bengio_ia_%C2%ABdes_prises 2025-02-08T08:58:34Z http://www.semanlink.net/doc/2023/04/yoshua_bengio_chercheur_%C2%AB_au Interviews concomitantes de Bengio et [LeCun](doc:2023/04/yann_le_cun_directeur_a_meta_) par le Monde > il n’est pas impossible que l’on parvienne à fabriquer un jour ce qui pourrait ressembler aux mécanismes de la [conscience](tag:conscience_artificielle) > On ne peut pas continuer avec des décisions qui, alors qu’elles touchent autant la société, sont laissées aux seules entreprises qui ont les moyens de développer ces outils 2023-04-29T14:27:31Z http://www.semanlink.net/doc/2023/04/yoshua_bengio_se_joint_aux_cent 2023-04-05T10:31:18Z http://www.semanlink.net/doc/2022/12/machine_learning_for_combinator 2022-12-09T14:27:32Z http://www.semanlink.net/doc/2021/08/deep_learning_for_ai_%7C_july_202 2021-08-02T15:48:37Z http://www.semanlink.net/doc/2021/07/2102_11107_towards_causal_rep 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 Related: [Making sense of raw input](doc:2021/05/making_sense_of_raw_input) 2021-07-15T00:29:21Z http://www.semanlink.net/doc/2021/03/equilibrium_propagation_bridgi 2021-03-19T13:32:54Z http://www.semanlink.net/doc/2020/04/2004_10151_experience_grounds 2020-04-22T16:52:37Z http://www.semanlink.net/doc/2020/02/yoshua_bengio [Yoshua Bengio’s blog – first words](https://yoshuabengio.org/2020/02/10/fusce-risus/) 2020-02-12T08:38:52Z http://www.semanlink.net/doc/2019/12/yoshua_bengio_revered_architec 2019-12-18T14:55:47Z http://www.semanlink.net/doc/2019/11/_1807_00082_amanuensis_the_pr **The use of natural language to facilitate communication between the expert programmer and apprentice AI system.** > an overview of the material covered in a course taught at Stanford in the spring quarter of 2018. The course draws upon **insight from cognitive and systems neuroscience to implement hybrid connectionist and symbolic reasoning systems** that leverage and extend the state of the art in machine learning **by integrating human and machine intelligence**. As a concrete example we focus on digital assistants that learn from continuous dialog with an expert software engineer while providing initial value as powerful analytical, computational and mathematical savants. > [#Dehaene](/tag/stanislas_dehaene)'s work extends the [#Global Workspace Theory](/tag/global_workspace_theory) of Bernard Baars. Dehaene’s version of the theory combined with Yoshua Bengio’s concept of a [#consciousness prior](/tag/consciousness_prior.html) and deep reinforcement learning suggest a model for constructing and maintaining the cognitive states that arise and persist during complex problem solving. 2019-11-12T16:25:10Z http://www.semanlink.net/doc/2019/10/feature_wise_transformations > 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**. Related to this talk at Paris NLP meetup: ["Language and Perception in Deep Learning"](/doc/2019/10/language_and_perception_in_deep) 2019-10-07T23:30:41Z http://www.semanlink.net/doc/2019/09/what_s_next_for_ai_yoshua_ben 2019-09-17T18:29:52Z http://www.semanlink.net/doc/2019/08/learning_structured_embeddings_ 2019-08-03T21:55:22Z http://www.semanlink.net/doc/2019/07/_1907_03950_learning_by_abstra > Given an image, we first predict a probabilistic graph that represents its underlying semantics and serves as a structured world model. Then, we perform sequential reasoning over the graph, iteratively traversing its nodes to answer a given question or draw a new inference. In contrast to most neural architectures that are designed to closely interact with the raw sensory data, our model operates instead in an abstract latent space, by transforming both the visual and linguistic modalities into semantic concept-based representations, thereby achieving enhanced transparency and modularity. > Drawing inspiration from [Bengio’s consciousness prior](/doc/?uri=https%3A%2F%2Farxiv.org%2Fabs%2F1709.08568)... 2019-07-10T22:05:52Z https://openreview.net/forum?id=rJXMpikCZ 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). 2018-11-14T02:10:45Z https://arxiv.org/abs/1605.07427 > 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 2018-11-14T01:42:02Z https://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf 2018-11-06T10:29:46Z http://www.iro.umontreal.ca/~bengioy/talks/MIT-18oct2018.pdf > Underlying Assumption: There are principles giving rise to intelligence (machine, human or animal) via learning, simple enough that they can be described compactly, similarly to the laws of physics, i.e., our intelligence is not just the result of a huge bag of tricks and pieces of knowledge, but of general mechanisms to acquire knowledge. 2018-10-23T22:41:09Z https://www.youtube.com/watch?v=Yr1mOzC93xs > **What's wrong with our unsupervised training objectives ? They are in pixel space rather than in abstract space** > Many more entropy bits in acoustics details than linguistic content. Related to [this paper](/doc/?uri=https%3A%2F%2Farxiv.org%2Fabs%2F1709.08568) 2018-09-28T22:21:15Z http://aclweb.org/anthology/Q16-1002 > 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) 2018-08-23T22:28:38Z http://www.deeplearningbook.org/contents/representation.html 2017-12-16T14:31:43Z http://www.deeplearningbook.org/ 2017-12-16T14:25:02Z https://www.quora.com/How-do-RBMs-work-What-are-some-good-use-cases-and-some-good-recent-papers-on-the-topic > 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 2017-10-30T12:36:20Z https://www.quora.com/How-does-one-apply-deep-learning-to-time-series-forecasting > 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 2017-10-22T13:45:32Z https://arxiv.org/abs/1709.08568 "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. [YouTube video](/doc/?uri=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DYr1mOzC93xs) 2017-09-29T14:44:19Z