Rasmus Berg Palm

Deep Learning, Machine Learning and Web tech.

• DeepLearnToolbox

  • October 2011 to Present
  Team Members: Rasmus Berg Palm

  Matlab toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets.

• jSlate

  • August 2011 to Present
  Team Members: Rasmus Berg Palm

  An open source web based dashboarding interface.
  
  Was picked up by h-online and gained a lot of traction early
  
  http://www.h-online.com/open/news/item/JavaScript-dashboard-framework-jSlate-open-sourced-1421756.html

• Bromine

  • 2006 to 2010
  Team Members: Rasmus Berg Palm, Visti Kløft, Jeppe Poss

  An open source web-based interface to run selenium tests and collect results.
  
  As of may 2012 more than 2.4 million tests have been run via Bromine.
  

• Erfaring med frivilligt arbejde

  • DevOps / Developer / QA / BI

    Roskilde Festival

    2007 – present (6 years)

    Lots of hats and responsibility in this tightly knit IT group doing internal systems for the festival. Proud member of the make-stuff-work team, i.e. DevOps.
    Making systems work from idea, through design, coding, testing, deploying, maintaining and monitoring.

• Prediction as a candidate for learning deep hierarchical models of data

  • Technical University of Denmark
  • March 28, 2012
  Authors: Rasmus Berg Palm

  Recent findings [HOT06] have made possible the learning of deep layered hier- archical representations of data mimicking the brains working. It is hoped that this paradigm will unlock some of the power of the brain and lead to advances towards true AI.
  In this thesis I implement and evaluate state-of-the-art deep learning models and using these as building blocks I investigate the hypothesis that predicting the time-to-time sensory input is a good learning objective. I introduce the Predictive Encoder (PE) and show that a simple non-regularized learning rule, minimizing prediction error on natural video patches leads to receptive fields similar to those found in Macaque monkey visual area V1. I scale this model to video of natural scenes by introducing the Convolutional Predictive Encoder (CPE) and show similar results. Both models can be used in deep architectures as a deep learning module.

• Bachelor of Engineering (B.E.), Biomedical/Medical Engineering

  Technical University of Denmark

  • Neurophysics
  • Applied signal processing
  • Introduction to statistics
  • Physics 2
  • Electrophysiology
  • Introduction to medical imaging
  • Modelling physiological systems
  • Introduction to clinical practice at hospitals
  • Physics 1
  • Basic subjects in biomechanics and biotransportation
  • Biomaterials
  • Signals and linear systems in continuous-time
  • Cellular biology
  • Science theory
  • Mathematics 2
  • Introductory programming in Matlab
  • Electronics and measurement technique
  • Musculoskeletal biomechanics
  • Mathematics 1
  • Basic chemistry
  • Materials science
  • Human biology and pathology
  • Physiological measurements and methods

• Master of Engineering (M.Eng.), Medical Engineering

  Technical University of Denmark

  • Stochastic Simulations
  • Cognitive Modelling
  • Machine learning and signal processing
  • Introduction to cognitive science
  • Medical-technological product developement
  • Statistics and planning experiments
  • Advanced subjects of signal processing
  • Advanced physiological modelling
  • Advanced signal processing with medical applications
  • Pathophysiology

1. Machine Learning
2. Signal Processing
3. Neuroscience
4. Cognitive Neuroscience
5. Computer Vision
6. Artificial Intelligence
7. PHP
8. Data Modeling
9. Matlab
10. Numerical Simulation
11. Java
12. JavaScript
13. Grails
14. CakePHP
15. Business Intelligence
16. Hudson
17. Jenkins
18. Puppet
19. Selenium

• English

  (Full professional proficiency)

• Danish

  (Native or bilingual proficiency)

Interesser:

strong AI, deep learning, machine learning, singularity, big data, crossfit, new technology

Grupper og sammenslutninger:

• 
  Artificial Intelligence
• 
  Machine Learning Connection
• 
  Pattern Recognition, Data Mining, Machine Intelligence and Learning