Tim Dettmers

Tim Dettmers is a masters student in informatics at the University of Lugano where he works on deep learning research. Before that he studied applied mathematics and worked for three years as a software engineer in the automation industry. He runs a blog about deep learning and takes part in Kaggle data science competitions where he has reached a world rank of 63.

Posts by Tim Dettmers

Figure 1: Value iteration constructs the value function over all states over time. Here each square is a state: S is the start state, G the goal state, T squares are traps, and black squares cannot be entered. In value iteration we initialize the rewards (traps and goal state) and then these reward values spread over time until an equilibrium is reached. Depending on the penalty value on traps and the reward value for the goal different solution patterns might emerge; the last two grids show such solution states.
Technical Walkthrough 0

Deep Learning in a Nutshell: Reinforcement Learning

This post is Part 4 of the Deep Learning in a Nutshell series, in which I’ll dive into reinforcement learning, a type of machine learning in which agents take… 28 MIN READ
CUDA AI Cube
Technical Walkthrough 0

Deep Learning in a Nutshell: Sequence Learning

This series of blog posts aims to provide an intuitive and gentle introduction to deep learning that does not rely heavily on math or theoretical constructs. 13 MIN READ
Technical Walkthrough 0

Deep Learning in a Nutshell: History and Training

This series of blog posts aims to provide an intuitive and gentle introduction to deep learning that does not rely heavily on math or theoretical constructs. 23 MIN READ
Technical Walkthrough 0

Deep Learning in a Nutshell: Core Concepts

This post is the first in a series I’ll be writing for Parallel Forall that aims to provide an intuitive and gentle introduction to deep learning. 19 MIN READ