== Neural Networks For Feature Analysis
=== Introductions

'''Mayank Barad'''[[BR]]Rising Senior in Computer Engineering and Computer Science

'''Daksh Khetarpaul'''[[BR]]Rising Junior in Computer Engineering


'''Katherine Lew'''[[BR]]Rising Sophomore in Finance and Computer Science


[[span(style=color: #A50000, '''Advisors''')]] - Dr Richard Howard, Dr Richard Martin

=== Project Description

Neural networks have a long history of being used for classification, and more recently. content generation, Example classifiers including, image classification between dogs and cats, text sentiment classification. Example generative networks include those for human faces, images, and text. Rather than classification or generation, this work explores using networks for feature analysis. Intuitively, features are the high level patterns that distinguish data, such as text and images, into different classes. Our goal is to explore bee motion datasets to qualitatively measure the ease or difficulty of reverse-engineering the features found by the neural networks.

=== Week 2

This week we visited the beehive to observe the behaviour of real bees so we can simulate a realistic synthetic bee.

[[Image(unnamed.jpg)]]

We named our first bee prototype as "Jitterbug" because it looks like an electrocuted bug as you can see

[[Image((jitterbug.mov)]]