Machine Learning and AI for Healthcare
#book #AI #ml

Team
@data_enthusiasts
@OpenArchiveBooks

CVPR 2021 paper

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion (MiVOS)

Paper:
https://arxiv.org/pdf/2103.07941v1.pdf

Github:
https://github.com/hkchengrex/MiVOS

Project page:
https://hkchengrex.github.io/MiVOS/

Team
@data_enthusiasts
@OpenArchiveBooks

Teach yourself Computer Engineering with YouTube

https://cs1000.vercel.app/


Team
@data_enthusiasts
@OpenArchiveBooks

🎯 Bayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees

Github: https://github.com/AaltoML/BayesNewton

Paper: https://arxiv.org/pdf/2111.01721v1

Team
@data_enthusiasts
@OpenArchiveBooks

#tip

Team
@data_enthusiasts
@OpenArchiveBooks

😃 GoEmotions: A Dataset for Fine-Grained Emotion Classification

Github: https://github.com/google-research/google-research/tree/master/goemotions

Google AI: https://ai.googleblog.com/2021/10/goemotions-dataset-for-fine-grained.html

Team
@data_enthusiasts
@OpenArchiveBooks

🎁Absolutely Free🎁

#deeplearning #beginner

http://introtodeeplearning.com/

Team
@data_enthusiasts
@OpenArchiveBooks

🚀 Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

Github: https://github.com/chongjiange/care

Paper: https://openreview.net/pdf?id=sRojdWhXJx

Dataset: https://paperswithcode.com/dataset/coco

Team
@data_enthusiasts
@OpenArchiveBooks

#tip

Team
@data_enthusiasts
@OpenArchiveBooks

Explore, Create and Share Learning Roadmaps in Tech

https://reallyconfused.co/

#resource

Team
@data_enthusiasts
@OpenArchiveBooks

🔹 Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning

Github: https://github.com/facebookresearch/Mask2Former

Installation: https://github.com/facebookresearch/Mask2Former/blob/main/INSTALL.md

Paper: https://arxiv.org/pdf/2112.01527v1

Dataset: https://paperswithcode.com/dataset/cityscapes

Team
@data_enthusiasts
@OpenArchiveBooks

Coding for non-programmers: Why we need better GUI automation tools

https://matduggan.com/why-we-need-better/

Team
@data_enthusiasts
@OpenArchiveBooks

🦎 → 🐍 NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

Github: https://github.com/GEM-benchmark/NL-Augmenter

Paper: https://arxiv.org/pdf/2112.02721v1

Dataset: https://paperswithcode.com/dataset/sst

Team
@data_enthusiasts
@OpenArchiveBooks

9 distance measures in data science

Team
@data_enthusiasts
@OpenArchiveBooks

Importance of Analytics in Manufacturing



Analytics plays a very important role in all industries and business sectors. From medical to educational to even a small shopkeeper, collecting and analyzing data is something that can’t be ignored. Let us try and understand what analytics is or what analytics means? In general definition, Analytics is the process of examining and analyzing data or statistics for the discovery, interpretation and communication of meaningful patterns in data. These data patterns are applied towards effective decision making. The importance of analytics in manufacturing is as relevant as how customers are to buyers.

Manufacturing Analytics is the proper use by gathering data from operations and events in the industry, analyzing it with the help of the advanced technologies such as, cloud-computing, digital twin, machine learning, AI, etc to ensure quality, increased performance and yield, reduced cost, and optimize supply chain. Manufacturing analytics is a part of the smart manufacturing sector which comes under the huge umbrella; Industry 4.0. It relies upon predictive analysis, big data analytics, the IoT, machine learning, and edge computing to enable smarter, scalable factory solutions. In short, Manufacturing Analytics is the collection and analysis of data from an unlimited number of sources to help manufacturing companies increase the productivity and profitability of their operations.

Manufacturing analytics provides access to manufacturers on the real-time contextual awareness, and thus gives decision makers a competitive edge by digitizing the business, optimizing costs, improving quality, accelerating innovations, and redefining customer experience. It is the conversion from data into insights into actions. That is, the analytics helps in identifying the business use cases (which include, supply chain, product quality, field service and support, creating an efficient factory), assembles the data which are collected from the factory floor, connected sensors and devices, the data for suppliers, sales, processes, equipment, etc. The assembled data is then put together, merged, cleansed, filtered, and prepared for analysis. The analyzed data helps to start the automation process and creates applications for real-time monitoring and dashboards, it also looks for signals that indicate defects, cycle time, production yield and other parameters and push-out alerts.

The rise in industrial automation in manufacturing, increased complexities in the supply chain, and growing demand for software systems that reduce time and cost. The current global manufacturing analytics market size is about $6 billion, which is predicted to reach $28.5 billion by 2026.

Manufacturing Analytics is a key factor in maintaining and conducting proper quality assurance at all stages of production. It helps in improving the quality of an end-product and increasing the production yield through anomaly detection. By adding the huge chunks of data collected from sensors, devices and AI visual inspection software within a powerful cloud-based manufacturing analytics platform, quality can be controlled at the micro level. Data science and advanced manufacturing analytics make it possible for this process to be simulated. Choosing the right solution for manufacturing analytics and quality checks includes many factors. For example, the software provided by Lincode for quality inspection, LIVIS, is a cost-effective, AI-based, easily deployable solution that collects and analyzes data to inspect the product and check for defects in less than a second. 

Let me know what you think about this through our Discussion Chat

Team
@data_enthusiasts
@OpenArchiveBooks

A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents

Github: https://github.com/extreme-classification/deepxml

Paper: https://arxiv.org/pdf/2111.06685v1

Dataset: https://paperswithcode.com/dataset/extreme-classification

Team
@data_enthusiasts
@OpenArchiveBooks

Don't be scared.. Math and Computing are friends

Team
@data_enthusiasts
@OpenArchiveBooks

💉 Semi-supervised-learning-for-medical-image-segmentation.

Github: https://github.com/HiLab-git/SSL4MIS

Paper: https://arxiv.org/pdf/2112.04894v1

Team
@data_enthusiasts
@OpenArchiveBooks

Know why big data analytics for small business is the future

https://medium.com/dataseries/know-why-big-data-analytics-for-small-business-is-the-future-377dea6cb519

Team
@data_enthusiasts
@OpenArchiveBooks

​​NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

This paper presents a new participatory Python-based natural language augmentation framework that supports the creation of transformations (modifications to the data) and filters (data splits according to specific features).

The current version of the framework contains 117 transformations and 23 filters for a variety of natural language tasks.

The authors demonstrate the efficacy of NL-Augmenter by using several of its transformations to analyze the robustness of popular natural language models.

Paper: https://arxiv.org/abs/2112.02721
Code: https://github.com/GEM-benchmark/NL-Augmenter

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-nlaugmenter

#deeplearning #nlp #augmentation #robustness

Team
@data_enthusiasts
@OpenArchiveBooks