You are here

MIA Talks

Practical recommendations for training convolutional neural nets

November 16, 2016
Beck Lab, Harvard Medical School

Deep learning, in particular convolutional neural network (ConvNet), is rapidly emerging as one of the most successful approaches for image and speech recognition. What distinguishes ConvNets and other deep learning systems from conventional machine learning techniques is their ability to learn the entire perception process from end to end. Deep learning systems use multiple nonlinear processing layers to learn useful representations of features directly from data.

Searching the parameter space of deep architectures is a complex optimization task. ConvNets can be very sensitive to the setting of their hyper-parameters and network architecture setting. In this talk, I will give practical recommendations for training ConvNets and discuss the motivation and principles behind them. I will also provide recommendations on how to tackle various problems in analyzing medical image data such as lack of data, highly skewed class distributions, etc.

Finally, I will introduce some of the advanced ConvNet architectures used in medical image analysis and their suitability for various tasks such as detection, classification, and segmentation.