Learning in modular systems

By J. Bagnell, David M. Bradley. 2010

39 citations recorded by the source corpus.

How researchers see this paper

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

In Model Architectures

Citations in the corpus

Convolutional Pose Machines (2016, background): “Composing multiple convolutional networks in a CPM results in an overall network with many layers that is at risk of the problem of vanishing gradients [4, 5, 10, 12] during learning.”
Data-dependent Initializations of Convolutional Neural Networks (2015, positive): “Glorot & Bengio (2010); Saxe et al. (2013); Sussillo & Abbot (2015); He et al. (2015); Bradley (2010) show that properly scaled random initialization can deal with the vanishing gradient problem, if the architectures are limited to linear transformations, followed by a very specific non-linearities.”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “[2013], Calinon et al. [2007], Khansari-Zadeh and Billard [2011], Paraschos et al.”
Barren plateaus in quantum neural network training landscapes (2018, background): “Finally, we contrast our results with the vanishing (and exploding) gradient problem of classical deep neural networks [32–34 , The gradient in a classical deep neural network can vanish exponentially in the number of layers [32, 33], while in the a quantum circuit is exponentially small in the…”
Understanding the difficulty of training deep feedforward neural networks (2010, background): “As first noted by Bradley (2009), we observe (Figure 7) that at the beginning of training, after the standard initialization (eq.”
UNCERTAINTY MODELING AND INTERPRETABILITY IN CONVOLUTIONAL NEURAL NETWORKS FOR POLYP SEGMENTATION (2018, background): “back-propagated gradients were smaller as one moves from the output layer towards the input layer, just after initialization [60].”
Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes (2016, background): “dules. In the 1970s, several researchers [6,27,51,60,64] proposed combining a low-level image segmentation module with a high-level image interpretation module. Recent works have looked at both joint [10,11,16,21,29,36,42,43,53,59,63,65] and sequential/cascaded [12,25,26,28,38,41] reasoning over dif”
VQE method: a short survey and recent developments (2021, background): “, gradient-vanishing) existed in the early studies of deep neural networks (Bradley et al. 2009; Shalev-Shwartz et al. 2017; Kremer and Kolen 2001) with mitigation techniques proposed later on (LeCun et al. 2015; Ioffe and Szegedy 2015; Hinton et al. 2006; He et al. 2016). Nevertheless, for hardware”