Unsupervised Segmentation With Dynamical Units

Rao, A. Ravishankar; Cecchi, Guillermo A.; Peck, Charles; Kozloski, James

doi:10.1109/tnn.2007.905852

Cited by 16 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The biological plausibility of this approach is reduced by the usage of complex-valued weights. Rao et al (2008); Rao & Cecchi (2010 propose a complex-valued neural network with real-valued weights. By training their network on images of individual objects, they enable it to separate overlapping objects of the same type on the test images.…”

Section: Related Workmentioning

confidence: 99%

Complex-Valued Autoencoders for Object Discovery

Löwe¹,

Lippe²,

Rudolph³

et al. 2022

Preprint

View full text Add to dashboard Cite

Object-centric representations form the basis of human perception and enable us to reason about the world and to systematically generalize to new settings. Currently, most machine learning work on unsupervised object discovery focuses on slot-based approaches, which explicitly separate the latent representations of individual objects. While the result is easily interpretable, it usually requires the design of involved architectures. In contrast to this, we propose a distributed approach to object-centric representations: the Complex AutoEncoder. Following a coding scheme theorized to underlie object representations in biological neurons, its complex-valued activations represent two messages: their magnitudes express the presence of a feature, while the relative phase differences between neurons express which features should be bound together to create joint object representations. We show that this simple and efficient approach achieves better reconstruction performance than an equivalent real-valued autoencoder on simple multi-object datasets. Additionally, we show that it achieves competitive unsupervised object discovery performance to a SlotAttention model on two datasets, and manages to disentangle objects in a third dataset where SlotAttention fails -all while being 7-70 times faster to train.

show abstract

Section: Related Workmentioning

confidence: 99%

Complex-Valued Autoencoders for Object Discovery

Löwe¹,

Lippe²,

Rudolph³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Using Non-oscillatory Dynamics to Disambiguate Pattern Mixtures

Achler

2012

The Relevance of the Time Domain to Neural Network Models

View full text Add to dashboard Cite

An oscillatory neural network model that demonstrates the benefits of multisensory learning

Rao

2018

Cogn Neurodyn

View full text Add to dashboard Cite

Since the world consists of objects that stimulate multiple senses, it is advantageous for a vertebrate to integrate all the sensory information available. However, the precise mechanisms governing the temporal dynamics of multisensory processing are not well understood. We develop a computational modeling approach to investigate these mechanisms. We present an oscillatory neural network model for multisensory learning based on sparse spatio-temporal encoding. Recently published results in cognitive science show that multisensory integration produces greater and more efficient learning. We apply our computational model to qualitatively replicate these results. We vary learning protocols and system dynamics, and measure the rate at which our model learns to distinguish superposed presentations of multisensory objects. We show that the use of multiple channels accelerates learning and recall by up to 80%. When a sensory channel becomes disabled, the performance degradation is less than that experienced during the presentation of non-congruent stimuli. This research furthers our understanding of fundamental brain processes, paving the way for multiple advances including the building of machines with more human-like capabilities.

show abstract

Unsupervised Segmentation With Dynamical Units

Cited by 16 publications

References 34 publications

Complex-Valued Autoencoders for Object Discovery

Complex-Valued Autoencoders for Object Discovery

Using Non-oscillatory Dynamics to Disambiguate Pattern Mixtures

An oscillatory neural network model that demonstrates the benefits of multisensory learning

Contact Info

Product

Resources

About