Deep Learning for Music Information Retrieval with Tensorflow2
Workshop Date:
Mon, 08/10/2020 - Fri, 08/14/2020
CANCELED
SUMMER 2020: All workshops offered will be done remotely, due to attempts to limit transmission of SARS-CoV-2. This workshop has been canceled, and may be offered again in summer 2021.
This workshop will cover the industry-standard methods to develop deep neural network architectures for digital audio. We will learn what's new in the latest version of Tensorflow 2. Throughout five immersive days of study, we will cover theoretical, mathematical, and practical principles that deep learning researchers use everyday in the real world. Our schedule will be:
Day 1: Learning mechanisms of feedforward neural networks
Math - Linear algebra and differential calculus review. The mathematics of feedforward neural networks.
Theory - How synaptic neuroplasticity inspired the backpropagation algorithm.Practice a) - Writing a feedforward neural network with backpropagation using numpy.
Practice b) - Automating differentiation with Tensorflow 2.
Day 2: Building blocks of deep learning architectures
Math - Activation functions. Norm functions. Convolution. Momentum.
Theory - Recurrent computations. Backpropagation through time. Convolutional layers. Gradient descent. Weight regularization. Best practices for parameter initialization.
Practice a) - Writing a recurrent neural network in Tensorflow 2.
Practice b) - Writing a convolutional neural network in Tensorflow 2.
Day 3: Training a state-of-the-art model for digital audio
Math - Basic probability. Gaussian distribution. Loss functions. MFCCs.
Theory - Feature embedding. Optimization algorithms. Batch normalization. The Keras library. Parallel GPU training. Tensorboard.
Practice a) - Optimizing a Convolutional Neural Network for music genre identification.
Practice b) - Optimizing a Recurrent Neural Network for automatic speech recognition.
Day 4: Audio generation and Machine translation
Math - Principal components analysis. Kulback-Leibler divergence.
Theory - Dilated convolutions. Dimensionality reduction. Variational autoencoders. Self-attention.
Practice a) - Audio generation with Wavenet
Practice b) - Audio generation with MusicVAE
Practice c) - Neural machine translation with the Transformer
Day 5: Capstone project
Math - Open for personalized review with the instructor.
Theory - Open for personalized review with the instructor.
Practice - Solve a problem of your choice with deep learning. Get personalized guidance from the instructor. Present your results to the class.
Who is this workshop for?
This course has been designed for students who want to gain serious experience using deep neural networks to solve digital audio problems with state-of-the-art performance. It is assumed that students have previous knowledge of linear algebra, differential calculus, and programming experience with python or matlab. Individuals who have previous experience with deep learning will also benefit from this workshop's emphasis on Tensorflow 2, which is the latest release of the industry standard library for deep learning research. Previous workshop attendees include engineers who are now working at tech companies like Apple, Microsoft, and Walmart Labs, as well as students who are now pursuing graduate studies in artificial intelligence at prestigious institutions all over the world.
About the instructor
Iran R. Roman is a theoretical neuroscientist and senior PhD candidate at CCRMA. He is a Stanford Human-Centered Artificial Intelligence PhD fellow. Iran is a passionate instructor, with extensive experience teaching artificial intelligence and deep learning at Stanford. His industry experience includes deep learning engineering internships at Plantronics in 2017, Apple in 2018 and 2019, and Oscilloscape in 2020. In industry, Iran has focused on using deep learning for speech recognition. Iran's PhD thesis is titled: "Mathematical models of anticipation and synchronization with periodic stimuli", where he simulates how the brain synchronizes with music using non-linear oscillators.