8,751 Hits in 3.2 sec

Other paths of the 20th century portuguse essay-writing: José Bacelar, Mário Sacramento and João Martins Pereira
Outros caminhos do ensaísmo português do século XX: José Bacelar, Mário Sacramento e João Martins Pereira

Joao Tiago Pedroso de Lima
2009 Revista Estudos do Século XX  
Joao Martins Pereira nao foge a esta regra.  ...  Nao estari Mario Sacramento a cometer, por sua ve:z, urna bela-injustifa?  ... 
doi:10.14195/1647-8622_9_11 fatcat:ahojvxf7sjdoja7magz3ys7wve

Beyond backpropagation: implicit gradients for bilevel optimization [article]

Nicolas Zucchet, João Sacramento
2022 arXiv   pre-print
Acknowledgements This research was supported by an Ambizione grant (PZ00P3 186027) from the Swiss National Science Foundation and an ETH Research Grant (ETH-23 21-1) awarded to João Sacramento.  ...  ., and Sacramento, J. (2021). A con- trastive rule for meta-learning. arXiv preprint arXiv:2104.01677. pp. 15, 16, 29, 35, and 38.  ... 
arXiv:2205.03076v1 fatcat:rdv5cjiconcp3fn6ra5dhmkguq

Resenha/ Review: RIBEIRO, Ana Paula Goulart e SACRAMENTO, Igor (orgs.). Mikhail Bakhtin: linguagem, cultura e mídia. São Carlos: Pedro & João, 2010, 429p

Anthony Wall
2011 Bakhtiniana: Revista de Estudos do Discurso  
It is hard to react other than positively to a publication, presented in Portuguese, conceived with the idea of introducing Bakhtin as re-invented in the Anglo-Saxon world to a Brazilian audience. Two Brazilian editors from Rio de Janeiro have put together a (sometimes) surprising mix containing some of the best-known English-writing critics working in the field of Bakhtin Studies (Michael Holquist, Ken Hirschkop, David Shepherd, Caryl Emerson) and several other relatively unknown ones. Such a
more » ... hoice of authors has the advantage of putting side-by-side writers hailing from various disciplines and oftentimes divergent academic horizons. It corresponds quite sharply with an important
doaj:5c2305a8b22c4b428a7229eff4ad306d fatcat:bkz4decf4rc43ps7gyirvua6re

Taxonomical Associative Memory

Diogo Rendeiro, João Sacramento, Andreas Wichert
2012 Cognitive Computation  
In a recent work, Sacramento and Wichert (in Neural Netw 24(2):143-147, 2011) proposed a hierarchical arrangement of compressed associative networks, improving retrieval time by allowing irrelevant neurons  ...  Sacramento Á A. Wichert INESC-ID and Instituto Superior Técnico, Technical University of Lisboa, Av. Prof. Dr.  ...  Moreover, alike the hierarchical retrieval prescription described in Sacramento and Wichert [1] , our taxonomical model yields a performance improvement over the original Willshaw network.  ... 
doi:10.1007/s12559-012-9198-4 fatcat:s4vwmbmlirgtjjkibunl5k4ilu

Dendritic cortical microcircuits approximate the backpropagation algorithm [article]

João Sacramento, Rui Ponte Costa, Yoshua Bengio, Walter Senn
2018 arXiv   pre-print
Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here, we introduce a multilayer neuronal network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output. In contrast to previous work our model does not require separate phases and
more » ... aptic learning is driven by local dendritic prediction errors continuously in time. Such errors originate at apical dendrites and occur due to a mismatch between predictive input from lateral interneurons and activity from actual top-down feedback. Through the use of simple dendritic compartments and different cell-types our model can represent both error and normal activity within a pyramidal neuron. We demonstrate the learning capabilities of the model in regression and classification tasks, and show analytically that it approximates the error backpropagation algorithm. Moreover, our framework is consistent with recent observations of learning between brain areas and the architecture of cortical microcircuits. Overall, we introduce a novel view of learning on dendritic cortical circuits and on how the brain may solve the long-standing synaptic credit assignment problem.
arXiv:1810.11393v1 fatcat:jetulqdayrdrtnbh4ejzfqtusq

Learning Bayes-optimal dendritic opinion pooling [article]

Jakob Jordan, João Sacramento, Willem A.M. Wybo, Mihai A. Petrovici, Walter Senn
2021 arXiv   pre-print
Pooling different opinions and weighting them according to their reliability is conducive to making good decisions. We demonstrate that single cortical neurons, through the biophysics of conductance-based coupling, perform such complex probabilistic computations via their natural dynamics. While the effective computation can be described as a feedforward process, the implementation critically relies on the bidirectional current flow along the dendritic tree. We suggest that dendritic membrane
more » ... tentials and conductances encode opinions and their associated reliabilities, on which the soma acts as a decision maker. Furthermore, we derive gradient-based plasticity rules, allowing neurons to learn to represent desired target distributions and to weight afferents according to their reliability. Our theory shows how neurons perform Bayes-optimal cue integration. It also explains various experimental findings, both on the system and on the single-cell level, and makes new, testable predictions for intracortical neuron and synapse dynamics.
arXiv:2104.13238v1 fatcat:gdis35qlhja6litbxdnujqotbm

Tree-like hierarchical associative memory structures

João Sacramento, Andreas Wichert
2011 Neural Networks  
Sacramento, A. Wichert / Neural Networks 24 (2011) 143-147  ... 
doi:10.1016/j.neunet.2010.09.012 pmid:20970304 fatcat:qtuqo5bcc5d4hjs72ycr7mhrsq

Conductance-based dendrites perform reliability-weighted opinion pooling [article]

Jakob Jordan, João Sacramento, Mihai A. Petrovici, Walter Senn
2020 arXiv   pre-print
Cue integration, the combination of different sources of information to reduce uncertainty, is a fundamental computational principle of brain function. Starting from a normative model we show that the dynamics of multi-compartment neurons with conductance-based dendrites naturally implement the required probabilistic computations. The associated error-driven plasticity rule allows neurons to learn the relative reliability of different pathways from data samples, approximating Bayes-optimal
more » ... vers in multisensory integration tasks. Additionally, the model provides a functional interpretation of neural recordings from multisensory integration experiments and makes specific predictions for membrane potential and conductance dynamics of individual neurons.
arXiv:2006.15099v1 fatcat:a23g7cko4ffnbcoj5d5jubkqxu

Dendritic error backpropagation in deep cortical microcircuits [article]

João Sacramento and Rui Ponte Costa and Yoshua Bengio and Walter Senn
2017 arXiv   pre-print
Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates the necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to
more » ... predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of pyramidal neurons where both long-range excitatory feedback and local inhibitory predictions are integrated. When local inhibition fails to match excitatory feedback an error occurs which triggers plasticity at bottom-up synapses at basal dendrites of the same pyramidal neurons. We demonstrate the learning capabilities of the model in a number of tasks and show that it approximates the classical error backpropagation algorithm. Finally, complementing this cortical circuit with a disinhibitory mechanism enables attention-like stimulus denoising and generation. Our framework makes several experimental predictions on the function of dendritic integration and cortical microcircuits, is consistent with recent observations of cross-area learning, and suggests a biological implementation of deep learning.
arXiv:1801.00062v1 fatcat:uruwi5mq3bgxdl7fgeokof55dm

Influência da queima controlada no pH do solo em povoamentos de Pinus spp, na região de Sacramento, MG

João Gomes Neto, Roando Viana Soares
1999 Ciência Florestal  
A pesquisa desenvolveu-se na região de Sacramento, Minas Gerais, em latossolo vermelho-amarelo, fase argilosa.  ...  MATERIAL E MÉTODOS Caracterização geral da área A região escolhida situa-se no município de Sacramento, área Chapadão do Bugre, Estado de Minas Gerais.  ...  Os povoamentos utilizados para a obtenção dos dados são pertencentes a fazenda "Chapadão do Bugre" de propriedade da empresa RESA -Reflorestadora Sacramento Ltda.  ... 
doi:10.5902/19805098312 fatcat:w4cel6qhdzheba4kmgsiryteie

The least-control principle for learning at equilibrium [article]

Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi, Johannes von Oswald, João Sacramento
2022 arXiv   pre-print
Sacramento.  ...  Acknowledgments and Disclosure of Funding This research was supported by an Ambizione grant (PZ00P3_186027) from the Swiss National Science Foundation and an ETH Research Grant (ETH-23 21-1) awarded to João  ...  Sacramento et al.  ... 
arXiv:2207.01332v1 fatcat:7ebqaqd6ubcfjpogppkwuufgri


João Antunes, João Borges da Costa, Manuel Sacramento Marques
2011 Revista da Sociedade Portuguesa de Dermatologia e Venereologia  
Borges da Costa, Manuel Sacramento Marques  ...  Psoriática Febre Reumática Doença Inflamatória Intestinal Doença de Lyme Artrite Séptica Sífilis Secundária Tuberculose GEIDST Artrite Reactiva (syn: Síndrome de Reiter) Joana Antunes, João  ... 
doi:10.29021/spdv.69.2.608 fatcat:puk6faymxbel3ffie3rqi35qci

Ghost Units Yield Biologically Plausible Backprop in Deep Neural Networks [article]

Thomas Mesnard, Gaetan Vignoud, Joao Sacramento, Walter Senn, Yoshua Bengio
2019 arXiv   pre-print
In the past few years, deep learning has transformed artificial intelligence research and led to impressive performance in various difficult tasks. However, it is still unclear how the brain can perform credit assignment across many areas as efficiently as backpropagation does in deep neural networks. In this paper, we introduce a model that relies on a new role for a neuronal inhibitory machinery, referred to as ghost units. By cancelling the feedback coming from the upper layer when no target
more » ... signal is provided to the top layer, the ghost units enables the network to backpropagate errors and do efficient credit assignment in deep structures. While considering one-compartment neurons and requiring very few biological assumptions, it is able to approximate the error gradient and achieve good performance on classification tasks. Error backpropagation occurs through the recurrent dynamics of the network and thanks to biologically plausible local learning rules. In particular, it does not require separate feedforward and feedback circuits. Different mechanisms for cancelling the feedback were studied, ranging from complete duplication of the connectivity by long term processes to online replication of the feedback activity. This reduced system combines the essential elements to have a working biologically abstracted analogue of backpropagation with a simple formulation and proofs of the associated results. Therefore, this model is a step towards understanding how learning and memory are implemented in cortical multilayer structures, but it also raises interesting perspectives for neuromorphic hardware.
arXiv:1911.08585v1 fatcat:dzvz2xnvovhyjgwa6qs524nz4y

Nephrogenic systemic fibrosis: mini-review

Juliano Sacramento Mundim, Sabrina de Castro Lorena, Rosilene Motta Elias, João Egídio Romão Júnior
2009 Clinics  
.: 55 11 3069.6570 NEpHROgENIc sysTEmIc fIbROsIs: mINI-REvIEw doi: 10.1590/S1807-59322009000500017 Juliano Sacramento Mundim, Sabrina de Castro Lorena, Rosilene Motta Elias, João Egídio Romão Júnior  ... 
doi:10.1590/s1807-59322009000500017 pmid:19488616 pmcid:PMC2694254 fatcat:srfv6kjd5fd7fjjvqww4vukcsm


Kleber Sacramento Adão, Alex Witney Lima
2011 Revista da ALESDE  
Palabras-clave: Fútbol; Prensa; São João del Rei.  ...  Palavras-chave: Futebol; Imprensa; São João del-Rei.  ...  João. (...).  ... 
doi:10.5380/alesde.v1i1.21399 fatcat:4yd7x4ow5bgtbbuiedv5abd5qu
« Previous Showing results 1 — 15 out of 8,751 results