-
Generative Adversarial Networks – Hot Topic in Machine Learning
What is Generative Adversarial Networks (GAN) ? A very illustrative explanation of GAN is presented here with simple examples like predicting next frame in video sequence or predicting next word while typing in google search.
-
3 methods to deal with outliers
In both statistics and machine learning, outlier detection is important for building an accurate model to get good results. Here three methods are discussed to detect outliers or anomalous data instances.
-
Privacy, Security and Ethics in Process Mining
Data Privacy, Security and Ethics are hot yet complex topics in the business and data science world. This important article talks about and provide guidelines for privacy, security and ethics, specifically in the context of Process Mining.
-
The Costs of Misclassifications
Importance of correct classification and hazards of misclassification are subjective or we can say varies on case-to-case. Lets see how cost of misclassification is measured from monetary perspective.
-
Data Analytics Models in Quantitative Finance and Risk Management
We review how key data science algorithms, such as regression, feature selection, and Monte Carlo, are used in financial instrument pricing and risk management.
-
The Best Metric to Measure Accuracy of Classification Models
Measuring accuracy of model for a classification problem (categorical output) is complex and time consuming compared to regression problems (continuous output). Let’s understand key testing metrics with example, for a classification problem.
-
Smart Data Platform – The Future of Big Data Technology
Data processing and analytical modelling are major bottlenecks in today’s big data world, due to need of human intelligence to decide relationships between data, required data engineering tasks, analytical models and it’s parameters. This article talks about Smart Data Platform to help to solve such problems.
-
 The hard thing about deep learning
It’s easy to optimize simple neural networks, let’s say single layer perceptron. But, as network becomes deeper, the optmization problem becomes crucial. This article discusses about such optimization problems with deep neural networks.
-
An Intuitive Explanation of Convolutional Neural Networks
This article provides a easy to understand introduction to what convolutional neural networks are and how they work.
-
Deep Learning cleans podcast episodes from ‘ahem’ sounds
“3.5 mm audio jack… Ahem!!” where did you hear that? ;) Well, this post is not about Google Pixel vs iPhone 7, but how to remove ugly “Ahem” sound from a speech using deep convolutional neural network. I must say, very interesting read.
|
The hard thing about deep learning