DeepAI AI Chat
Log In Sign Up

Superposition as Data Augmentation using LSTM and HMM in Small Training Sets

by   Akilesh Sivaswamy, et al.

Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition augmentation and compared with plain default training and mix-up augmentation. This augmentation technique originates from the mix-up approach but provides more solid theoretical reasoning based on quantum properties. We achieved 3 number of training samples in Russian audio-digits recognition task and 7,16 better accuracy than mix-up augmentation by training only 500 samples using HMM on the same task. Also, we achieved 1.1 900 samples in MNIST using 3-layer stacked LSTM.


page 1

page 2

page 3

page 4


Self-paced Data Augmentation for Training Neural Networks

Data augmentation is widely used for machine learning; however, an effec...

Mixup of Feature Maps in a Hidden Layer for Training of Convolutional Neural Network

The deep Convolutional Neural Network (CNN) became very popular as a fun...

A Bayesian Data Augmentation Approach for Learning Deep Models

Data augmentation is an essential part of the training process applied t...

Understanding data augmentation for classification: when to warp?

In this paper we investigate the benefit of augmenting data with synthet...

Learning audio and image representations with bio-inspired trainable feature extractors

Recent advancements in pattern recognition and signal processing concern...

Chronological Self-Training for Real-Time Speaker Diarization

Diarization partitions an audio stream into segments based on the voices...

Towards Robust Waveform-Based Acoustic Models

We propose an approach for learning robust acoustic models in adverse en...