Lending direction to neural networks

By Richard S. Zemel, Christopher K. I. Williams, Michael C. Mozer. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, background): “Successful integrations include complex-valued Boltzmann Machines (Reichert and Serre, 2014; Zemel et al., 1995) and complex-valued RNNs that could be trained either with backpropagation (Mozer et al.”
Neuronal Synchrony in Complex-Valued Deep Networks (2013, methodology): “…model of neuronal interactions. sages also naturally leads to different synchronous groups emerging: for excitatory connections, messages that ‘agree’ (Zemel et al., 1995) in their phases prevail over those that do not; inhibitory messages, on the other hand, equate to excitatory messages of…”
Exponential Family Harmoniums with an Application to Information Retrieval (2004, background): “Some exponential family extensions of general Boltzmann machines were proposed in [2], [ 15 ], but they do not have the bipartite structure that we study here.”
Lending Orientation to Neural Networks for Cross-View Geo-Localization (2019, methodology): “While our method to be described in this paper was originally inspired by paper [35], we find it unsuitable for the task of image-based localization, for two reasons.”
Deep Complex Networks (2017, background): “As pointed out in Reichert and Serre [2013], the use of complex-valued neural networks [Georgiou and Koutsougeras, 1992, Zemel et al., 1995, Kim and Adalı, 2003, Hirose, 2003, Nitta, 2004] has been investigated long before the earliest deep learning breakthroughs [Hinton et al., 2006, Bengio et…”
Transformation Equivariant Boltzmann Machines (2011, methodology): “Our work should not be confused with the directional unit Boltzmann machine (DUBM) network of Zemel et al [14].”
Bayesian Optimization and Semiparametric Models with Applications to Assistive Technology (2014, background): “Encoding such periodic signals in a parametric neural network and blending this with unsupervised learning can be challenging [Zemel et al., 1995].”
Nonparametric guidance of autoencoder representations using label information (2012, background): “Encoding such periodic signals in a parametric neural network and blending this with unsupervised learning can be challenging (Zemel et al., 1995).”