Zobrazeno 1 - 10
of 254
pro vyhledávání: '"Van Gerven, Marcel A. J."'
Autor:
Doerig, Adrien, Sommers, Rowan, Seeliger, Katja, Richards, Blake, Ismael, Jenann, Lindsay, Grace, Kording, Konrad, Konkle, Talia, Van Gerven, Marcel A. J., Kriegeskorte, Nikolaus, Kietzmann, Tim C.
Artificial Neural Networks (ANNs) inspired by biology are beginning to be widely used to model behavioral and neural data, an approach we call neuroconnectionism. ANNs have been lauded as the current best models of information processing in the brain
Externí odkaz:
http://arxiv.org/abs/2209.03718
In this paper we introduce the temporally factorized 3D convolution (3TConv) as an interpretable alternative to the regular 3D convolution (3DConv). In a 3TConv the 3D convolutional filter is obtained by learning a 2D filter and a set of temporal tra
Externí odkaz:
http://arxiv.org/abs/2006.15983
Traditional backpropagation of error, though a highly successful algorithm for learning in artificial neural network models, includes features which are biologically implausible for learning in real neural circuits. An alternative called target propa
Externí odkaz:
http://arxiv.org/abs/2006.06438
We propose a solution to the weight transport problem, which questions the biological plausibility of the backpropagation algorithm. We derive our method based upon a theoretical analysis of the (approximate) dynamics of leaky integrate-and-fire neur
Externí odkaz:
http://arxiv.org/abs/2003.03988
Perceived personality traits attributed to an individual do not have to correspond to their actual personality traits and may be determined in part by the context in which one encounters a person. These apparent traits determine, to a large extent, h
Externí odkaz:
http://arxiv.org/abs/1912.09831
Publikováno v:
Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), Brussels, Belgium, November 6-8, 2019
3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D convolutional kernels efficiently requiring less training data. We ach
Externí odkaz:
http://arxiv.org/abs/1912.04075
Quasi-experimental research designs, such as regression discontinuity and interrupted time series, allow for causal inference in the absence of a randomized controlled trial, at the cost of additional assumptions. In this paper, we provide a framewor
Externí odkaz:
http://arxiv.org/abs/1911.06722
In daily life situations, we have to perform multiple tasks given a visual stimulus, which requires task-relevant information to be transmitted through our visual system. When it is not possible to transmit all the possibly relevant information to hi
Externí odkaz:
http://arxiv.org/abs/1907.12309
In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Taylor-corrected estimators usin
Externí odkaz:
http://arxiv.org/abs/1904.00469
Autor:
Ambrogioni, Luca, Güçlü, Umut, Berezutskaya, Julia, Borne, Eva W. P. van den, Güçlütürk, Yağmur, Hinne, Max, Maris, Eric, van Gerven, Marcel A. J.
In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortized variational inference is a likelihood-free method as its gradient ca
Externí odkaz:
http://arxiv.org/abs/1805.11542