Browsed by
Tag: CNN

New Weighted Evaluation Metric for Semantic Segmentation Algorithms P1

New Weighted Evaluation Metric for Semantic Segmentation Algorithms P1

In this post, we will understand the importance of needing a new evaluation metric in healthcare AI, but before jumping directly let’s set some context of what, where, and how. Usage of AI has increased substantially in healthcare lately as it is able to assist doctors in diagnosing patients better. It is able to give much more insightful data which doctors dint even think of using to diagnose. Many medical institutions are collaborating with big companies and start-ups to solve…

Read More Read More

K-Means clustering of MNIST dataset

K-Means clustering of MNIST dataset

Updates as on 16th Jan 2020: Improved clustering accuracy to 98.5% using a simpler CNN model mentioned in Keras page. And instead of extracting a feature vector from the final activation layer, we should take the output of the layer just before the final activation layer. In this post, we will be clustering MNIST digits dataset using the K-Means algorithm with accuracy close to 90%. And also we will understand different aspects of extracting features from images, and see how…

Read More Read More