Target Class Learning for Anomaly/Outlier Detection: a robust strategy
Instructors: P Nagabhushan, Sonali Agarwal, Sanjay Sonbhadra, Narinder Singh Punn
Machine learning techniques have advanced exponentially in recent years. These improved technologies are adopted in several application domains. An anomaly is an abnormal pattern that exists in the data and in all real-time applications, anomaly detection is the most crucial task. The anomaly or outlier detection task becomes more challenging when only the target class (class of interest) samples are available during training and other class samples are either ill-defined or absent. In this context, several solutions have been offered, but despite the extensive technological developments, anomaly/novelty detection is still a challenging task and there is enough scope to mimic the learning behaviour of the human brain. Following the capability of the brain to simultaneously analyze the anomaly, one-class classification strategies are adopted for better learning of the target class. Apart from the huge sample space, the high dimension of the data adds computational overhead along with its intrinsic property of curse of dimensionality. The learning models exhibit better performance in the presence of the most promising training samples and discriminating features. The selection of training samples and features must be supervised by only the target class samples to ensure strong separation from outliers. With this motivation, this tutorial presents the recent advancements in target class learning for anomaly detection while covering fundamentals, use-cases, applications, and challenges. The tutorial also discusses future research possibilities and necessary challenges. See more ….

AI techniques to combat COVID-19
Instructors: Sonali Agarwal, Narinder Singh Punn, Sanjay Sonbhadra
The rampant outbreak of the novel coronavirus (COVID-19, SARS-Cov-2), during early December 2019 in Wuhan, China, has created a staggering worldwide crisis along with the widespread loss of lives. The scarcity of resources and lack of experiences to endure the COVID-19 pandemic, combined with the fear of future consequences has established the need for adoption of Artificial Intelligence (AI) techniques to address the challenges. Motivated by the need to highlight the need for employing AI in combating the COVID-19 pandemic, this tutorial aims to help the audience to gain comprehensive understanding of the current state of AI applications in developing the computer-assisted (controlling, monitoring, discovery, diagnosing and treatment) systems to battle the COVID-19 crisis along with the AI assisted spread containment measures. See more ….

Biomedical image segmentation using deep learning
Instructors: Sonali Agarwal, Krishna Pratap Singh, Narinder Singh Punn, Sanjay Sonbhadra
Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. Most of the medical applications require identifying and localizing the objects or regions (damaged tissues, cells or nuclei) found in the medical imaging such as CAT scans, X-Rays, Ultrasound, etc. for diagnosis, monitoring and treatment. This delineation is generally performed by expert clinicians or radiologists which is a complex and time-consuming task. In recent studies, the implication of transfer learning and U-Net based approaches have illustrated state-of-the-art performance in different applications for the development of computer-aided diagnosis systems to localize the infected or damaged tissues or cells in the body using various modalities for early diagnosis and treatment of diseases such as brain tumor, lung cancer, alzheimer, breast cancer, etc. With this motivation, this tutorial focuses on the state-of-the-art in Transfer and Deep Learning, a critical discussion of open challenges and directions for future research in the area of biomedical image segmentation. See more …
.

Software Testing and Quality Assurance for Data Intensive applications
Instructors: Sonali Agarwal, Sanjay Sonbhadra, Narinder Singh Punn,
With the advancements in technology various real-time applications are developed with big data analytics solutions. The efficient function of such data intensive solutions is very critical and hence it is necessary to perform desired software testing and get quality assurance before it is put into use. Following this motivation, this tutorial aims to unfold the various testing and quality assurance strategies along with the awareness about existing tools and techniques that can be utilized for various use cases. See more …
.

MultiModal learning: A new paradigm for machine intelligence
Instructors: Sonali Agarwal, Sanjay Sonbhadra, Narinder Singh Punn,
Deep learning technologies have advanced exponentially in recent years. These improved technologies are adopted in several domains for various applications. Despite the extensive developments, there is still scope for improvements to mimic the learning behaviour of the human brain. Following the capability of the brain to simultaneously analyze the various data types, multimodal learning strategies are adopted for better feature representations and overall learning of the model. In this, a learning model uses several data sources such as image, text, video, audio, etc. to exploit rich information and improve the learning capability of the models. With this motivation, this tutorial presents the recent advancements in multimodal learning while covering fundamentals, usecases, applications and challenges. The tutorial also covers the future research directions to unfold the possibilities of novel approaches while addressing the necessary challenges. See more …
.

Multilayer Network Visualization: Theory and applications
Instructors: Sonali Agarwal, Sanjay Sonbhadra, Narinder Singh Punn,
The proposed tutorial is intended to provide a detailed coverage of contemporary multi-layer network visualization techniques to support the understanding of various existing complex systems. The tutorial is covering basics of multilayer networks along with various techniques of visualization under faceting perspective, application perspective and system perspective. Besides several use cases of multilayer networks and critical challenges incurred while developing multi-layer graph visualization will also be covered. Furthermore, future research directions are uncovered to address such challenges. This tutorial will definitely attract the researchers’ attention since multilayer networks are expected to play a significant role in the study of complex systems in the future. By bringing the visualization community closer to the application domains as well as the complex systems communities, better outcomes will be achieved for all stakeholders. See more …
.

Unrevealing Data Correlations with Self-Supervised Learning
Instructors: Sonali Agarwal, Sanjay Sonbhadra, Narinder Singh Punn,
Deep learning has brought the most profound contribution towards living standards by addressing several real-world problems. The continuous advancements in the approaches for classification, localization, segmentation, detection, etc. have extended its application spectrum across various domains. To accomplish such tasks, the models are required to be trained using a huge amount of annotated or labelled data. However, the generation of the annotations for such huge data requires expert analysts and extensive manual efforts. It is a tedious and expensive task, while also being vulnerable to error. Self-supervised learning is an emerging technology that advances to address this issue by effectively closing the gap with fully supervised methods. Here, the aim is to perform pre-training with an unsupervised strategy for learning useful and better representations of the data samples. The pre-trained model is then fine-tuned with limited annotated samples to adopt the actual task such as segmentation, classification, etc. In light of this, the present tutorial discovers various self-supervised learning strategies that could be utilized to improve the performance of the deep learning models. See more …
.