Name: Jakob Drachmann Havtorn
Type: User
Company: @corticph
Bio: Industrial PhD researcher within machine learning, uncertainty quantification, and speech processing.
Twitter: JakobHavtorn
Location: Copenhagen, Denmark
Blog: https://jakobhavtorn.github.io/
Jakob Drachmann Havtorn's Projects
Implementations of various algorithms and data structures
Toy implementations of some Bayesian Optimization algorithms
Official source code repository for the paper "Benchmarking Generative Latent Variable Models for Speech"
A small example of how translational equivariance and invariance work in CNNs
Simulation of a computer from scratch in Python based on the Crash Course: Computer Science YouTube series.
Study group repository for evolutionary strategies
Evolutionary computing and variational optimization for training neural networks
Solutions for Project Euler problems
Example of FastAPI usage
Bash script for getting personal Fitbit data
Mapping of author created learning objectives to official common academic goals
Some fun with Hamming Codes
Official source code repository for the ICML 2021 paper "Hierarchical VAEs Know What They Don't Know"
Personal website for Jakob Havtorn
My Master's Thesis on Variational Optimization of Neural Networks written at the Technical University of Denmark
Implementation of neural network modules in numpy
Fun with transcripts of Philosophize This!
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Utilities for pytorch models, dataloaders etc.
Interfacing with SemanticScholar API
Fun with seam carving
Sequential Monte Carlo Methods PhD Course
A script to switch CUDA version for the fish
Notes and exercises from A Tour of Go
Transformer seq2seq model, program that can build a language translator from parallel corpus
Uncertainty Quantification in Deep Learning
Proceedings of ICML 2021
Out of distribution modelling with variational methods
Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"