Convolutional Neural Networks are a category of Neural Networks that have proven very effective in the computer vision field. ConvNets have proven successful in image classification, identifying faces, object and traffic signs apart from powering vision in robots and self driving cars. ConvNets, therefore, are an important tool for most machine learning engineers today. However, understanding ConvNets and learning to use them can sometimes be an intimidating experience.
The primary purpose of this talk is to explain how ConvNets work and how we can train them efficiently to resolve some important computer vision problems.