Author Archives: Jayita Bhattacharyya

10 Jan

Microsoft Releases Unadversarial Examples: Designing Objects for Robust Vision – A Complete Hands-On Guide

image-19104
image-19104

In a recent work by Microsoft Research, a new framework is introduced which can address in the case of unforeseen corruptions or distribution shifts of data models to create “unadversarial objects,” inputs that are optimized particularly for more robust model performance.

The post Microsoft Releases Unadversarial Examples: Designing Objects for Robust Vision – A Complete Hands-On Guide appeared first on Analytics India Magazine.

07 Jan

Hands-On Guide To Adversarial Robustness Toolbox (ART): Protect Your Neural Networks Against Hacking

image-19060
image-19060

The Adversarial Robustness Toolbox(ART) is a Python library which is one of the complete resources providing developers and researchers for evaluating the robustness of deep neural networks against adversarial attacks

The post Hands-On Guide To Adversarial Robustness Toolbox (ART): Protect Your Neural Networks Against Hacking appeared first on Analytics India Magazine.

06 Jan

Guide To Sktime – Python Library For Time Series Data (Compatible With Sci-kit learn)

image-19028
image-19028

Sktime is a unified python framework/library providing API for machine learning with time series data and sklearn compatible tools to analyse, visualize, tune and validate multiple time series learning models such as time series forecasting, time series regression and classification.

The post Guide To Sktime – Python Library For Time Series Data (Compatible With Sci-kit learn) appeared first on Analytics India Magazine.

1 2 8