New paper from Dr. Ghosh’s group
Title: Holographic QFTs on AdS$_d$, wormholes and holographic interfaces.
arXiv preprint: https://arxiv.org/abs/2209.12094
We consider three related topics: (a) Holographic quantum field theories on AdS spaces. (b) Holographic interfaces of flat space QFTs. (c) Wormholes connecting generically different QFTs. We investigate in a concrete example how the related classical solutions explore the space of QFTs and we construct the general solutions that interpolate between the same or different CFTs with arbitrary couplings. The solution space contains many exotic RG flow solutions that realize unusual asymptotics, as boundaries of different regions in the space of solutions. We find phenomena like “walking” flows and the generation of extra boundaries via “flow fragmentation”.
Understanding The Transcriptomic Responses to Environmental Change in Hilsa
In order to gain an in-depth understanding of the change in Hilsa migration, adaptation and reproduction emanating from climate change an integrated omics (genomics, transcriptomics, proteomics, metabolomics and metagenomics) approach has to be adopted. Use and development of different bioinformatics algorithms, tools, and scripts as well as high-performance computing facilities are required to analyze these omics datasets. Moreover, GIS and Remote sensing technologies are required to identify deep sea habitats and collect samples. Here at AGenCy lab IUB, we made connections with the group, led by Professor Haseena Khan, who were responsible for first sequencing of Hilsa. In this project, we will work in direct collaboration with this group. Professor Haseena Khan and her team will lead the sample collection, quality control and sequence data generation and analysis. We at IUB, in collaboration with Dr. A Baten from AgResearch, NZ and Professor M Shoyaib from IIT, DU will lead the computational analysis of the data extracted. In this project we aim to focus on the first phase of the integrated omics approach
Image Generation Using Variational Autoencoders and Energy Based Models
Machine learning practitioners have long sought generative models that can accurately estimate the underlying data distribution and are able to produce diverse and semantically meaningful image samples. In this project, we take part in a similar quest. Our research directions include (but not limited to) developing improved variational inference techniques, coming up with more efficient methods to train energy based models and better traversing the latent space with Riemannian geometry and manifold assumption.
Predicting Association Between Entities in Heterogeneous Biological Networks
Heterogeneity is inherent in biological networks which consist of different entities as nodes (i.e., genes, diseases, drugs, function) and represent the relationships between these entities as edges. Predicting potential associations between biological entities currently has been an important problem in biomedical research. In general, a deep learning model uses the contextual information and structures of the heterogeneous networks to identify the associations. This project will utilize powerful tools, e.g., GNN & MRF, to develop a more accurate, explainable model for link predictions in heterogeneous networks. Dr. Azad Abul Kalam will collaborate with us on this project.
Bangla Natural Language Processing
In this project, we intend to build a speaker independent Text-to-Speech (TTS) system in Bangla language. To solve the task, we will utilize the SOTA TTS model, Tacotron 2. This model is a combination of two neural network architectures: a modified Tacotron 2 model which is a recurrent sequence-to-sequence model with attention that generates mel-spectrograms from input text. And, a flow-based neural network model named WaveGlow. In this regard, we have created a multi-speaker TTS dataset for Bangladesh Bengali (bn-BD) and Indian Bengali (bn-IN) from Open Speech and Language Resources (OpenSLR) dataset. In our initial experiment, we are interested in the bn-BD dataset. It has audio data of 6 different speakers and corresponding text. Dr. Md Iftekhar Tanveer and Dr. Syeda Sakira Hassan are collaborating with us in this project.
Deep Learning On Graph Data
Nowadays, Graph Representation Learning has seen incredible success across a wide range of modern applications such as recommendation systems, drug discovery, computer vision, particle physics, combinatorial optimization, human activity recognition, etc. In general, a graph consists of nodes and edges where edges depict the relationship between nodes. For instance, the users are nodes in a social network, and edges represent their friendship/interactions. In brief, Graph Neural Networks (GNNs) are designed to compute the low dimensional meaningful embeddings for nodes/graphs through utilizing the structural information and node attributes (if available). These latent representations are used in different downstream tasks e.g., node classification, graph classification, link prediction, community detection/clustering, etc. The high-impact applications of GNNs are leading the research towards developing more advanced deep learning methods. In the high-level view, we aim to leverage probabilistic graphical models, self-supervision learning, contrastive learning, tensor decomposition, and Bayesian modeling into developing more robust, interpretable, and explainable GNNs.
LULC analysis of Bangladesh using Deep Learning
Land use land cover (LULC) is defined how the land is used by humans or what the surface is covered with. Specifically, land use means how a particular land is being used for; for example, farmland, built-up etc. Land Cover refers to what the surface is covered with; it can be river, forest, mountains etc. Thus, LULC information and LULC change over a period of time obtained from satellite data can be used to analyze the geography, socio-economic condition, poverty estimation, urban planning, building categorization etc. In this project we aim to obtain accurate LULC data from satellite images using deep learning methods. Deep learning based methods have been proved to be more effective to extract LULC information compared to traditional classifiers that are still used in GIS systems for this purpose. However, in order to train deep learning methods on satellite images we need to have a good amount of images annotated with ground-truth. For the LULC segmentation task we need pixel by pixel LULC class annotation for the satellite images. The goal of this project is to produce good quality LULC annotation data pixel by pixel for Dhaka city and surrounding area. With a sufficiently trained segmentation model, we can employ this model to perform LULC over the entire Bangladesh without any human effort. Moreover, this project targets to develop segmentation models that can outperform the existing ones by a significant margin.
