ApproxDBN: Approximate Computing for Discriminative Deep Belief Networks

By Xiaojing Xu, Srinjoy Das, Kenneth Kreutz-Delgado. 2017

3 citations recorded by the source corpus.

Probabilistic generative neural networks are useful for many applications, such as image classification, speech recognition and occlusion removal. However, the power budget for hardware implementations of neural networks can be extremely tight. To address this challenge we describe a design methodology for using approximate computing methods to implement Approximate Deep Belief Networks (ApproxDBNs) by systematically exploring the use of (1) limited precision of variables; (2) criticality analysis to identify the nodes in the network which can operate with such limited precision while allowing the network to maintain target accuracy levels; and (3) a greedy search methodology with incremental retraining to determine the optimal reduction in precision to enable maximize power savings under user-specified accuracy constraints. Experimental results show that significant bit-length reduction can be achieved by our ApproxDBN with constrained accuracy loss.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

How researchers see this paper

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

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, background): “For example, in [98], Gensler et al. investigate the performance of several DL models, such as DBNs, AEs, and LSTMs, as well as multilayer perceptron (MLP) for predicting the solar power of 21 photovoltaic plants.”
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review (2023, unknown): “An approximated DBN is presented in [172].”