Learning Generative Models with the Up Propagation Algorithm
Up-propagation is an algorithm for inverting and learning neural network generative models Sensory input is processed by inverting a model that generates patterns from hidden variables using topdown connections The inversion process is iterative utilizing a negative feedback loop that depends on an error signal propagated by bottomup connections The error signal is also used to learn the generative model from examples The algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorit…
Bayesian InferenceLearning to Adapt by Minimizing Discrepancy
We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neurocognitively-grounded approach in the cont…
Analytically Tractable Inference in Deep Neural Networks
Since its inception, deep learning has been overwhelmingly reliant on backpropagation and gradient-based optimization algorithms in order to learn weight and bias parameter values. Tractable Approximate Gaussian Inferenc…
Computational EfficiencyNature-Inspired Local Propagation
The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections. On the opposite, intelligent processes in nature arises without the need for such coll…
FusedProp: Towards Efficient Training of Generative Adversarial Networks
Generative adversarial networks (GANs) are capable of generating strikingly realistic samples but state-of-the-art GANs can be extremely computationally expensive to train. In this paper, we propose the fused propagation…