Applied Data Science and Machine Learning (ADSML)
PG Level Advanced Certification Programme in Applied Data Science and Machine Learning
Machine Learning
Accelerated Sequence Design of Star Block Copolymers: An Unbiased Exploration Strategy via Fusion of Molecular Dynamics Simulations and Machine Learning
Star block copolymers (s-BCPs) have potential applications as novel surfactants or amphiphiles for emulsification, compatibilization, chemical transformations, and separations. s-BCPs have chain architectures where three …
TOMBoost: a topic modeling based boosting approach for learning with class imbalance
Hypergraph partitioning using tensor eigenvalue decomposition
Hypergraphs have gained increasing attention in the machine learning community lately due to their superiority over graphs in capturing super-dyadic interactions among entities. In this work, we propose a novel approach …
MultiCens: Multilayer network centrality measures to uncover molecular mediators of tissue-tissue communication
With the evolution of multicellularity, communication among cells in different tissues and organs became pivotal to life. Molecular basis of such communication has long been studied, but genome-wide screens for genes and …
Q4 2022
Q3 2022
AI and data science centers in top Indian academic institutions
research-article Free AccessAI and data science centers in top Indian academic institutions Authors: B. Ravindran Indian Institute of Technology Madras, India Indian Institute of Technology Madras, IndiaView Profile , …
Byzantine Spectral Ranking
Multi-Variate Time Series Forecasting on Variable Subsets
Domain-Agnostic Constrastive Representations for Learning from Label Proportions
Q2 2022
Integration of machine learning and first principles models
Abstract Model building and parameter estimation are traditional concepts widely used in chemical, biological, metallurgical, and manufacturing industries. Early modeling methodologies focused on mathematically capturing …
Q1 2022
Scaling graph representation learning algorithms in an implementation agnostic fashion
--Prof. Srinivasan Parthasarathy-- A graph, which consists of nodes and edges, is a pictorial representation of the relationship between various objects. Analysis of graphs can help in inferring social, biological, …
On Combining Bags to Better Learn from Label Proportions
In the framework of learning from label proportions (LLP) the goal is to learn a good instance-level label predictor from the observed label proportions of bags of instances. Most of the LLP algorithms either explicitly …
Inductive Bias of Gradient Descent for Weight Normalized Smooth Homogeneous Neural Nets
We analyze the inductive bias of gradient descent for weight normalized smooth homogeneous neural nets, when trained on exponential or cross-entropy loss. We analyse both standard weight normalization (SWN) and …
Accurate and Interpretable AI models: Towards Deployable AI
A self-driving car bumps into a lamppost. A doctor prescribes the wrong treatment to a patient based on an AI-based diagnostic tool. A missile is misfired by an AI-based defense system. An unfair decision provided by a …
Q4 2021
Q3 2021
Interpretable AI
--Prof. Cynthia Rudin-- For quite a long time, researchers and the public were thrilled by the wonders of machine learning. However, over the period of time, the community realized that the machine learning models …
Machine Learning for Robot Locomotion: Grounded Learning and Adaptive Parameter Learning
--Dr.Peter Stone-- Robot locomotion continues to remain a challenging problem in spite of the advances in the field. To gain more insights on the topic, a talk on “Machine Learning for Robot Locomotion: Grounded …
Q2 2021
Q1 2021
Revisiting Link Prediction on Heterogeneous Graphs with A Multi-view Perspective
An Enhanced Advising Model in Teacher-Student framework using State Categorization
The teacher-student framework aims to improve the sample efficiency of RL algorithms by deploying an advising mechanism in which a teacher helps a student by guiding its exploration. Prior work in this field has …
Q4 2020
Data Driven Monitoring of Water Distribution Networks
Monitoring and control of water distribution networks requires measurements of flow and other process parameters. The upcoming model of Internet of Things (IoT) based devices involves several thousands of sensors and …
Domain agnostic methods for integration of prior knowledge in learning algorithms
There has been a tremendous shift in recent years in data analysis applications, where reasoning about systems is moving from the use of domain knowledge and data to the use of purely data-based analysis. This shift has …
Aided Selection of Sampling Methods for Imbalanced Data Classification
Building an effective classifier for imbalanced data is a challenging task as most of classifier work on the assumption of balanced data. Therefore, several sampling methods have been devised to bridge this gap by …
Q4 2020-2021
Q3 2020
Consistent plug-in classifiers for complex objectives and constraints
We present a consistent algorithm for constrained classification problems where the objective (e.g. F-measure, G-mean) and the constraints (e.g. demographic parity fairness, coverage) are defined by general functions of …
Hypergraph clustering by iteratively reweighted modularity maximization
Abstract Learning on graphs is a subject of great interest due to the abundance of relational data from real-world systems. Many of these systems involve higher-order interactions (super-dyadic) rather than mere pairwise …
Q2 2020
Inductive Bias of Gradient Descent for Exponentially Weight Normalized Smooth Homogeneous Neural Nets
We analyze the inductive bias of gradient descent for weight normalized smooth homogeneous neural nets, when trained on exponential or cross-entropy loss. Our analysis focuses on exponential weight normalization (EWN), …
Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks
Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity. In this paper, we propose a pipeline for understanding vehicle behaviour from a monocular image sequence or video. …
HPRA: Hyperedge Prediction using Resource Allocation
Many real-world systems involve higher-order interactions and thus demand complex models such as hypergraphs. For instance, a research article could have multiple collaborating authors, and therefore the co-authorship …
Machine Learning Applications for Mass Spectrometry-Based Metabolomics
The metabolome of an organism depends on environmental factors and intracellular regulation and provides information about the physiological conditions. Metabolomics helps to understand disease progression in clinical …
D y VED eep
Deep Neural Networks (DNNs) have advanced the state-of-the-art in a variety of machine learning tasks and are deployed in increasing numbers of products and services. However, the computational requirements of training …
Predicting software defect type using concept-based classification
PlotQA: Reasoning over Scientific Plots
Existing synthetic datasets (FigureQA, DVQA) for reasoning over plots do not contain variability in data labels, real-valued data, or complex reasoning questions. Consequently, proposed models for these datasets do not …
EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks
Ensuring robustness of Deep Neural Networks (DNNs) is crucial to their adoption in safety-critical applications such as self-driving cars, drones, and healthcare. Notably, DNNs are vulnerable to adversarial attacks in …
Conducting Non-adaptive Experiments in a Live Setting: A Bayesian Approach to Determining Optimal Sample Size
Abstract This research studies the use of predetermined experimental plans in a live setting with a finite implementation horizon. In this context, we seek to determine the optimal experimental budget in different …
Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization
In response to recent criticism of gradient-based visualization techniques, we propose a new methodology to generate visual explanations for deep Convolutional Neural Networks (CNN) - based models. Our approach - …
Interpretability With Accurate Small Models
Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, …
Novel ratio-metric features enable the identification of new driver genes across cancer types
ABSTRACT An emergent area of cancer genomics has been the identification of driver genes. Driver genes confer a selective growth advantage to the cell and push it towards tumorigenesis. Functionally, driver genes can be …
Comparison of first trimester dating methods for gestational age estimation and their implication on preterm birth classification in a North Indian cohort
Abstract Background Different formulae have been developed globally to estimate gestational age (GA) by ultrasonography in the first trimester of pregnancy. In this study, we develop an Indian population-specific dating …
Rate of change analysis for interestingness measures
A New Measure of Modularity in Hypergraphs: Theoretical Insights and Implications for Effective Clustering
Graph Convolutional Network with Sequential Attention for Goal-Oriented Dialogue Systems
Domain-specific goal-oriented dialogue systems typically require modeling three types of inputs, namely, (i) the knowledge-base associated with the domain, (ii) the history of the conversation, which is a sequence of …
Q4 2019
Extra: Transfer-guided exploration
Studying the plasticity in deep convolutional neural networks using random pruning
Pack and Detect
Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy …
Network-based features enable prediction of essential genes across diverse organisms
Machine learning approaches to predict essential genes have gained a lot of traction in recent years. These approaches predominantly make use of sequence and network-based features to predict essential genes. However, …
Q4 2018
On Controllable Sparse Alternatives to Softmax
Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms …
Consistent algorithms for multiclass classification with a reject option
We consider the problem of n-class classification (n≥2), where the classifier can choose to abstain from making predictions at a given cost, say, a factor α of the cost of misclassification. Designing consistent …
Dynamic Action Repetition for Deep Reinforcement Learning
An autoencoder approach to learning bilingual word representations
Harish Guruprasad
Harish Guruprasad is a Assistant Professor at Department of Computer Science & Engineering, IIT Madras. He received his B.Tech in Electrical Engineering from College of Engineering Guindy, Anna University, and his ME …
Balaraman Ravindran
Prof. Ravindran is the head of the Robert Bosch Centre for Data Science and Artificial Intelligence (RBC-DSAI) at IIT Madras and a professor in the Department of Computer Science and Engineering. He is also the …