How to Train Your Deep Neural Network with Dictionary Learning

TL;DR

This paper introduces a novel method for training deep neural networks using dictionary learning as the foundational building block, offering competitive performance on benchmark and real-world classification tasks.

Contribution

It proposes a new framework that replaces traditional training methods like RBMs and autoencoders with dictionary learning, including label consistent dictionary learning for the final classification layer.

Findings

Achieves top 10 results on benchmark datasets.

Outperforms existing techniques in age and gender classification.

Demonstrates flexibility with various dictionary learning types.

Abstract

Currently there are two predominant ways to train deep neural networks. The first one uses restricted Boltzmann machine (RBM) and the second one autoencoders. RBMs are stacked in layers to form deep belief network (DBN); the final representation layer is attached to the target to complete the deep neural network. Autoencoders are nested one inside the other to form stacked autoencoders; once the stcaked autoencoder is learnt the decoder portion is detached and the target attached to the deepest layer of the encoder to form the deep neural network. This work proposes a new approach to train deep neural networks using dictionary learning as the basic building block; the idea is to use the features from the shallower layer as inputs for training the next deeper layer. One can use any type of dictionary learning (unsupervised, supervised, discriminative etc.) as basic units till the pre-final layer. In the final layer one needs to use the label consistent dictionary learning formulation for classification. We compare our proposed framework with existing state-of-the-art deep learning techniques on benchmark problems; we are always within the top 10 results. In actual problems of age and gender classification, we are better than the best known techniques.