Ultimate Parallel and Distributed Computing with Julia For Data Science: Excel in Data Analysis, Statistical Modeling and Machine Learning by leveraging MLBase.jl and MLJ.jl to optimize workflows (English Edition)
This book takes you through a step-by-step learning journey, starting with the essentials of Julia’s syntax, variables, and functions. You’ll unlock the power of efficient data handling by leveraging Julia arrays and DataFrames.jl for insightful analysis. Develop expertise in both basic and advanced statistical models, providing a robust toolkit for deriving meaningful data-driven insights. The journey continues with machine learning proficiency, where you’ll implement algorithms confidently using MLJ.jl and MLBase.jl, paving the way for advanced data-driven solutions. Explore the realm of Bayesian inference skills through practical applications using Turing.jl, enhancing your ability to extract valuable insights. The book also introduces crucial Julia packages such as Plots.jl for visualizing data and results. The handbook culminates in optimizing workflows with Julia’s parallel and distributed computing capabilities, ensuring efficient and scalable data processing using Distributions.jl, Distributed.jl and SharedArrays.jl. This comprehensive guide equips you with the knowledge and practical insights needed to excel in the dynamic field of data science and machine learning.
@book{dash2024ultimate,title={Ultimate Parallel and Distributed Computing with Julia For Data Science: Excel in Data Analysis, Statistical Modeling and Machine Learning by leveraging MLBase.jl and MLJ.jl to optimize workflows (English Edition)},author={Dash, Nabanita},isbn={9789391246860},url={https://books.google.ca/books?id=b1bsEAAAQBAJ},year={2024},publisher={Orange Education Pvt Limited}}
×
[RE] A Reproducibility Study on Scene-Graph Generation from 3D Point Clouds: Hybrid Approach with Clip, 2D Image Semantics, and 3D Geometry
Nabanita Dash
Submitted to Transactions on Machine Learning Research, 2024
This paper scrutinizes the reproducibility of VL-SAT and multimodal learning systems for 3D semantic scene graph prediction. Leveraging visual (ViT, CLIP) and linguistic semantics, our study replicates top-k accuracy results and explores models like SGFN, and SGGPoint. We assess the impact of the CLIP adapter, 2D image semantics, and conduct hyperparameter tuning. Additionally, the ablation study investigates node and edge collaboration, and the influence of a multi-head self-attention network within the VL-SAT architecture, enhancing understanding of these critical components.
@article{anonymous2024re,title={[{RE}] A Reproducibility Study on Scene-Graph Generation from 3D Point Clouds: Hybrid Approach with Clip, 2D Image Semantics, and 3D Geometry},author={Dash, Nabanita},journal={Submitted to Transactions on Machine Learning Research},year={2024},url={https://openreview.net/forum?id=uqQGhTyTN7},note={Under review}}
Cloud forensics is the application of digital forensics in cloud computing as a subset of network forensics to gather and preserve evidence that’s suitable for presentation during a court of law. Cloud computing is the on-demand delivery of IT resources over the Internet with pay-as-you-go pricing. Instead of buying, owning, and maintaining physical data centers and servers, you’ll access technology services, like computing power, storage, and databases, on an as-needed basis from a cloud provider. In this report, we present detailed research to investigate the issues in forensics relating to cloud computing and present possible solutions.
@inproceedings{iot-paper,title={Digital Forensics Research on Cloud Computing},author={Dash, Nabanita and Pandya, Priya},year={2020},organization={ResearchGate, IIIT-BBSR},url={http://dx.doi.org/10.13140/RG.2.2.13516.01928}}
