Deep learning bioinformatics at Mærsk Tårnet
Two teaching days for the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen, running from the perceptron to a recurrent model for blood glucose.
The record for this visit is a University of Copenhagen reimbursement form, a hotel folio and a folder of phone photographs. Together they date the work to 30 May and 1 June 2018. The host was Gopal Karemore at the Novo Nordisk Foundation Center for Protein Research, and the form gives the purpose in five words: Guest Lecture Deep Learning Bioinformatics.
Teaching took place at Mærsk Tårnet, the tower attached to the Panum complex on Blegdamsvej. Two photographs taken at 09:15 on 1 June put the visit in the lift lobby, in front of the wayfinding wall that lists the tenants floor by floor. Auditoriums and teaching rooms sit on the first floor, the Novo Nordisk Foundation Center for Basic Metabolic Research holds six, seven and eight, and a viewpoint sits on the fifteenth.
The second day is still legible in the files. The slides run from a single artificial neuron to the perceptron, then activation functions, cost functions, gradient descent and backpropagation, coded by hand in Python before any use of TensorFlow. Two MNIST notebooks follow, one a plain network and one convolutional. A third builds LSTM and GRU layers in Keras over 13,642 blood glucose readings and asks the model for the next value. Alongside them sit the Pima Indians diabetes table, 768 rows and eight columns, and a paper on deep learning for protein-ligand binding affinity prediction.
No photograph of the teaching survives. The camera came out in the lobby, once over the rooftops from a high floor, and again in town on the last afternoon. The folder marked Day 1, 30 May is empty. What holds the first day in place is the folio from the Avenue Hotel on Åboulevard: arrival 30 May, departure 2 June, room 315, the guest name misspelt as Tarun Singh.
The money trail was filed on 19 July 2018 on the University of Copenhagen form for foreign guests. Taxis, meals, a train to the airport and extra hotel charges, receipts totalling 1,445.69 kroner, all ten of them photographed in one sitting seven weeks after the event.
Photographs by Tarry Singh, iPhone X
Names the contact at the Center for Protein Research, destination Copenhagen, purpose Guest Lecture Deep Learning Bioinformatics, trip 29 May to 2 June 2018.
Åboulevard 29, Frederiksberg. Arrival 30 May 2018, departure 2 June 2018, room 315.
Introduction to Neural Networks deck of 84 slides, two MNIST notebooks, and a Keras LSTM and GRU notebook forecasting blood glucose.
Development and evaluation of a deep learning model for protein-ligand binding affinity prediction.
