Classification of Quasars, Galaxies, and Stars in the Mapping of the Universe Multi-modal Deep Learning

05/22/2022
by   Sabeesh Ethiraj, et al.
0

In this paper, the fourth version the Sloan Digital Sky Survey (SDSS-4), Data Release 16 dataset was used to classify the SDSS dataset into galaxies, stars, and quasars using machine learning and deep learning architectures. We efficiently utilize both image and metadata in tabular format to build a novel multi-modal architecture and achieve state-of-the-art results. In addition, our experiments on transfer learning using Imagenet weights on five different architectures (Resnet-50, DenseNet-121 VGG-16, Xception, and EfficientNet) reveal that freezing all layers and adding a final trainable layer may not be an optimal solution for transfer learning. It is hypothesized that higher the number of trainable layers, higher will be the training time and accuracy of predictions. It is also hypothesized that any subsequent increase in the number of training layers towards the base layers will not increase in accuracy as the pre trained lower layers only help in low level feature extraction which would be quite similar in all the datasets. Hence the ideal level of trainable layers needs to be identified for each model in respect to the number of parameters. For the tabular data, we compared classical machine learning algorithms (Logistic Regression, Random Forest, Decision Trees, Adaboost, LightGBM etc.,) with artificial neural networks. Our works shed new light on transfer learning and multi-modal deep learning architectures. The multi-modal architecture not only resulted in higher metrics (accuracy, precision, recall, F1 score) than models using only image data or tabular data. Furthermore, multi-modal architecture achieved the best metrics in lesser training epochs and improved the metrics on all classes.

READ FULL TEXT

page 1

page 4

research
05/14/2022

Classification of Astronomical Bodies by Efficient Layer Fine-Tuning of Deep Neural Networks

The SDSS-IV dataset contains information about various astronomical bodi...
research
02/10/2021

Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning

Transfer learning from ImageNet is the go-to approach when applying deep...
research
09/20/2023

Using Artificial Intelligence for the Automation of Knitting Patterns

Knitting patterns are a crucial component in the creation and design of ...
research
10/09/2021

Embed Everything: A Method for Efficiently Co-Embedding Multi-Modal Spaces

Any general artificial intelligence system must be able to interpret, op...
research
03/01/2023

Speeding Up EfficientNet: Selecting Update Blocks of Convolutional Neural Networks using Genetic Algorithm in Transfer Learning

The performance of convolutional neural networks (CNN) depends heavily o...
research
03/08/2021

Deep Transfer Learning for WiFi Localization

This paper studies a WiFi indoor localisation technique based on using a...
research
11/18/2019

Neural Forest Learning

We propose Neural Forest Learning (NFL), a novel deep learning based ran...

Please sign up or login with your details

Forgot password? Click here to reset