Deep neural networks, particularly the convolutional neural network, have been applied effectively across a range of medical applications, including in dermatology, radiology, cardiology and ophthalmology.
The convolutional neural network, and its deep variants, is introduced for image analysis. A focus is placed on the intuition of such models, and why they are effective in practice.
TensorFlow is Google’s open-source framework for developing, learning and training neural networks, and it is widely employed.
The basic concepts of neural networks are introduced, with a focus on intuition. The simpler and widely used logistic regression model is introduced first, and from this the neural network is introduced as a generalization.