Hands-on Guide to Bayesian Neural Network in Classification

Bhoomika Madhukar Bayesian Neural Network

Consider an example where you are trying to classify a car and a bike. If an image of a truck is shown to the network, it ideally should not predict anything. But, because of the softmax function, it assigns a high probability to one of the classes and the network wrongly, though confidently predicts it to be a car. In order to avoid this, we use the Bayesian Neural Network (BNN).

The post Hands-on Guide to Bayesian Neural Network in Classification appeared first on Analytics India Magazine.

06 Aug

Using Grad-CAM to Visually Verify the Performance of CNN Model

Bhoomika Madhukar Developers Corner

We can all agree that Convolutional neural networks have proven to be very proficient in tasks like image classification, face recognition and document analysis. But with increasing efficiency and complexity, there is a gradual decrease in the interpretability of these algorithms. A solution to problems like face recognition involves hundreds of layers and thousands of…

The post Using Grad-CAM to Visually Verify the Performance of CNN Model appeared first on Analytics India Magazine.