A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.


Hello there!


Introducing mle-logging: A Lightweight Logger for ML Experiments 📖

14 minute read


There are few things that bring me more joy, than automating and refactoring code, which I use on a daily basis. It feels empowering (when done right) and can lead to some serious time savings. The motto: ‘Let’s get rid of boilerplate’. One key ingredient to my daily workflow is the logging of neural network training learning trajectories and their diagnostics (predictions, checkpoints, etc.).

Evolving Neural Networks in JAX

33 minute read


“So why should I switch from <insert-autodiff-library> to JAX?”. The classic first passive-aggressive question when talking about the new ‘kid on the block’. Here is my answer: JAX is not simply a fast library for automatic differentiation. If your scientific computing project wants to benefit from XLA, JIT-compilation and the bulk-array programming paradigm – then JAX provides a wonderful API.

Meta-Policy Gradients: A Survey

35 minute read


Most learning curves plateau. After an initial absorption of statistical regularities, the system saturates and we reach the limits of hand-crafted learning rules and inductive biases. In the worst case, we start to overfit. But what if the learning system could critique its own learning behaviour?

The Lottery Ticket Hypothesis: A Survey

38 minute read


Metaphors are powerful tools to transfer ideas from one mind to another. Alan Kay introduced the alternative meaning of the term ‘desktop’ at Xerox PARC in 1970. Nowadays everyone - for a glimpse of a second - has to wonder what is actually meant when referring to a desktop. Recently, Deep Learning had the pleasure to welcome a new powerful metaphor: The Lottery Ticket Hypothesis (LTH).

A Machine Learning Workflow for the iPad Pro

20 minute read


The iPad is a revolutionary device. I take all my notes with it, read & annotate papers and do most of my conceptual brainstorming on it. But how about Machine Learning applications? In todays post we will review a set of useful tools & venture into the love story of the iPad Pro & the new Raspberry Pi (RPi).

Getting started with JAX (MLPs, CNNs & RNNs)

30 minute read


JAX, Jax, JaX. Twitter seems to know nothing else nowadays (next to COVID-19). If you are like me and want to know what the newest hypetrain is about - welcome to todays blog post!

My Top 10 Deep RL Papers of 2019

22 minute read


2019 - What a year for Deep Reinforcement Learning (DRL) research - but also my first year as a PhD student in the field. Like every PhD novice I got to spend a lot of time reading papers, implementing cute ideas & getting a feeling for the big questions. In this blog post I want to share some of my highlights from the 2019 literature.

Cognitive Computational Neuroscience 2019 - A Mini-Report

23 minute read


TL;DR: This blog post provides an overview of trends & events from the Cognitive Computational Neuroscience (CCN) 2019 conference held in Berlin. It summarizes the keynote talks and provides my perspective and thoughts resulting from a set of stimulating days. More specifically, I cover recent trends in Model-Based RL, Meta-Learning and Developmental Psychology adventures. You can find all my notes here.

Forward Mode Automatic Differentiation & Dual Numbers

21 minute read


Automatic Differentiation (AD) is one of the driving forces behind the success story of Deep Learning. It allows us to efficiently calculate gradient evaluations for our favorite composed functions. TensorFlow, PyTorch and all predecessors make use of AD. Along stochastic approximation techniques such as SGD (and all its variants) these gradients refine the parameters of our favorite network architectures.

A Primer on Deep Q-Learning

33 minute read


Before starting to write a blog post I always ask myself - “What is the added value?”. There is a lot of awesome ML material out there. And a lot of duplicates as well. Especially when it comes to all the flavors of Deep Reinforcement Learning. So you might wonder what is the added value of this two part blog post on Deep Q-Learning? It is threefold.

EEML 2019 - A (Deep) Week in Bucharest!

11 minute read


In January I was considering where to go with my scientific future. Struggling whether to stay in Berlin or to go back to London, I got frustrated with my technical progress. At NeuRIPS I encountered so much amazing work and I felt like there was too much to learn until reaching the cutting edge. I was stuck. And then my former Imperial supervisor forwarded me an email advertising this new Eastern European Machine Learning (EEML) summer school.

Representational Similarity - From Neuroscience to Deep Learning… and back again

11 minute read


In today’s blog post we discuss Representational Similarity Analysis (RSA), how it might improve our understanding of the brain as well as recent efforts by Samy Bengio’s and Geoffrey Hinton’s group to systematically study representations in Deep Learning architectures. So let’s get started!

Steal, Stole, Stolen - A ML Perspective!

7 minute read


Hola guapos! After finally deciding to stay in Berlin, I felt the desire to structure myself and to establish routines which are going to help me tackle the next phase of my life. Due to a fortunate visit to the National Gallery book store in London, I got to pick up Austin Kleon’s amazing piece of work “Steal Like an Artist”. A beautifully collected and visualized set of tricks to foster creativity.

Barcelona GSE Articles and Interviews

less than 1 minute read


Hey there! As some of you might know I have been quite actively contributing to the Data Science Barcelona GSE blog. Writing about technical topics and addressing a broad audience is challenging and fulfilling at the same time. I hope that this blog is going to help me learn to tell great narratives and influence people. So stay tuned!


I got accepted into the SCIoI Excellence Cluster!


I got accepted into the Science of Intelligence Excellence Cluster! Starting in October 2019 I will be working on the project “Learning of Intelligent Swarm Behavior” under the supervision of Henning Sprekeler and Pawel Romanczuk. I am very happy to receive such generous funding and support from the excellence cluster.

I will stay affiliated with the Einstein Center for Neurosciences. Furthermore, my work will combine strong evidence from cognitive neuroscience and animal psychology in order to study the computational basis of coordination and adaptation in large collectives.

I will be giving a Talk @ENCODS FENS PhD Symposium!


I am happy to announce that I will be giving a short talk at the ENCODS FENS PhD Symposium about the “Neural Suprise in Human Somatosensation” project I have been working on during my first ECN lab rotation together with Sam Gijsen, Miro Grundei, Dirk Ostwald and Felix Blankenburg. If you are interested in more details and the general paradigm, check out our GitRepo.

RAAI Conference & EEML - I am coming!


Bucharest - I am coming! Very happy to attend the Recent Advances in Artificial Intelligence conference from 28th to 30th of June. I will present my work on Deep Multi-Agent RL for swarm dynamics in a poster session. Furthermore, my work has also been selected to be presented at the super-duper awesome EEML summer school. Can’t wait to meet the hero of temporal abstractions Doina Precup and Mr “Policy Distillation” Andrei Rusu.

Kick-Off ‘Flexible Learning’ Reading Group @TUBerlin


Last week we got to kick-off our new “Flexible Learning” reading group at the Technical University Berlin where we cover recent papers in Meta-/Transfer-/Continual & Self-supervised Learning! We started by reading the latest first-author paper by Yoshua Bengio connecting Meta-Learning with causal inference.

You can join our mailing list for more infos: click here.

Here are all the relevant infos for the next meeting:

Massive thanks goes out to the co-organizing help of Thomas Goerttler, Joram Keijser & Nico Roth! Hit me up if you are interested in joining!

Action Grammars are going to CCN!


Super exciting news! Parts of my masters’s thesis project (supervised by Professor Aldo Faisal) got accepted at the Cognitive Computational Neuroscience conference 2019. We combine Hierarchical Reinforcement Learning & Grammar Induction to define a set of temporally-extended actions… aka an Action Grammar! The resulting temporal abstractions can be used to efficiently tackle imitation, transfer and online learning.

Check out the preprint here! I am still in the process of extending the experiments and already looking forward to the poster presentations in Berlin (13th to 16th of September). The code will be open sourced as well. Hit me up if you are interested in the full story!

OIS Award Final Pitch Selection!


I am really excited to share that my project proposal on “Deep Swarm Shepherding - Benevolent Adaptation of Collective Behavior” has been selected for the final round of the Open Innovation in Science Award of the Einstein Center for Neurosciences Berlin. The goal of the award is to facilitate projects which fuse Open Innovation and Open Science in the context of neuroscience. It is jointly co-organized by the Ludwig Boltzmann Gesellschaft’s Open Innovation in Science Center (LBG OIS Center), QUEST and SPARK-Berlin.

I am very honored and am looking forward to all the 3 minute pitches! If you are interested in learning more about how I intend to make the world a better place by combining Behavioral Tracking, Inverse Reinforcement Learning and Machine Theory of Mind come by. The final round of the selection process will be publicly carried out - here are all the key information:

  • Location: Charité Campus Mitte, Charité CrossOver (CCO), Charitéplatz 1, 10117 Berlin.
  • Date and Time: Thursday, October 10, 2019, 16:00-18:15 (official part), doors open at 15:45.

Action Grammars @NeurIPS Workshops!


Super excited to share that my Master’s thesis project with Aldo Faisal got accepted to both the ‘Deep Reinforcement Learning’ & the ‘Learning Transferable Skills’ Workshop at NeurIPS 2019. I will be presenting the work within the DRL workshop in Vancouver and December!

Check out the updated preprint here & let me know if you have any ideas/questions. Furthermore, code to replicate the results may be found here.

Love, Rob

P.S.: Here is my previous poster from CCN:

Rob joins for.AI :heart:


I am really excited to announce that I have joined for.AI as an independent researcher. for.AI is a mainly-remote coordinated international group of ML researchers. One aim - the production of useful & effective ML research.

I am very much looking forward to new ideas, enthusiastic discussions and fruitful collaborations :hugs:! Such a great idea for the 21st century!

Love, Rob

P.S.: You can check out my solution to the coding challenge (comparing different pruning techniques) here!

Visual-ML-Notes Launch :pencil2:


Really happy to share Visual-ML-Notes ✍️ a virtual gallery of sketchnotes taken at Machine Learning talks 🧠🤓🤖 which includes last weeks #ICLR2020.

Explore, exploit & feel free to share: :point_right: website 💻 & the repository 📝



P.S.: There will be an entire blogpost dedicated to how I go about sketching, the workflow and the post-processing. Stay tuned :heart:

Rob @Virtual MLSS :school:


I am really happy to be attending the virtual edition of the MLSS Tübingen summer school where I will be presenting my most recent work on ‘Time Limits in Meta-Reinforcement Learning’. Get in touch if you want to chat about science, arts and ethology! Also I am looking forward to adding a new album to #visual-ml-notes 📝



Rob’s 1st Podcast - ML Street Talk :microphone:


Dear virtual world,

Last week I got to do my very first podcast. Exciting, right? I had a great time discussing my journey from Econ to ML & Collective Behaviour, social notions of intelligence & the Lottery Ticket Hypothesis! Thanks for having a podcast newbie! Checkout the full podcast by Tim Scarfe, Connor Shorten and Yannic Kilcher here:



Learning not to Learn @MetaLearning NeurIPS Workshop


I am very happy to be presenting my recent work on “Learning not to learn: Nature versus nurture in silico” at the NeurIPS Meta Learning workshop. We investigate the interplay of ecological uncertainty, task complexity and expected lifetime on the amortized Bayesian inference performed by memory-based meta learners. Checkout the preprint and feel free to drop me a note or hangout at the poster sessions on December, 11th.

Rob @Virtual M2L :school:


Happy new year! I am really happy to be attending the virtual (and first) edition of the Mediterranean Machine Learning (M2L) summer school. Get in touch if you want to chat about JAX, evolutionary algorithms or meta-learning! And stay tuned for some new #visual-ml-notes 📝 Big thank you to the organizers!



Talk @Warwick PhD Statistics Seminar


I got to give a talk :speech_balloon: about my recent work on meta-learning not to learn at the University of Warwick PhD Statistics Seminar.

You can check out the pre-print here: Link.

Talk @MIT Michael Carbin’s Lab


I got to give a talk :speech_balloon: about my recent work on lottery tickets in Deep Reinforcement Learning at Michael Carbin’s lab at MIT. Big thank you goes out to Jonathan Frankle for the kind invitation. This is joint work with my outstanding MSc student Marc A. Vischer and my supervisor Henning Sprekeler. Watch out for the pre-print!

ML Street Talk :microphone: Episode with Tom Zahavy


I had the honour to interview Dr. Tom Zahavy in the recent ML Street Talk episode together with Tim Scarfe and Yannic Kilcher. We discuss meta-gradients, JAX and the hardware lottery as well as the state and future of Deep RL. Check out the full episode here:

Rob @Medium TDS Featured Authors Series :bookmark:


I had a great time talking to Towards Data Science about my path into Machine Learning. We talk about my transition from Economics to Data Science and Computational Neuroscience. It is an honour to be part of the ‘Featured Authors Series’. You can check out the full Medium interview here!

Lottery Tickets in DRL @NERL ICLR Workshop


I am very happy to be presenting our recent work “On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning” at the ICLR ‘A Roadmap to Never-Ending RL’ workshop. We investigate the lottery ticket phenomenon in Deep Reinforcement Learning and provide evidence that most of the RL ticket effect can be attributed to the discovered pruning mask. Furthermore, the input layer mask discovered by Iterative Magnitude Pruning yields minimal task-sufficient representations. This mask can be used as a pair of “goggles” that compresses the representation. Dense agents trained on such a representation attain comparable performance at lower computational costs.

Checkout the preprint and feel free to drop me a note or hangout at the poster sessions on May, 7th. This is joint work with the phenomenal Master student Marc Vischer and my supervisor Henning Sprekeler.

Rob @CCN Algonauts Challenge Talk


I am very happy to be presenting my 5th place submission to the Algonauts Challenge during the CCN Algonauts workshop next Tuesday (September 7th, 1.30pm UTC-4/EDT). The solution is based on SimCLR-v2 features and a Bayesian Optimization pipeline for the encoding models:

Checkout my challenge report and code repository and feel free to drop me a note. Thank you very much to the organizers and fellow algonauts for this great experience.

Update: You can watch the YouTube replay here:



RandNLA for Generalized Linear Models with Big Datasets

Published in UPF/UAB Public Online Repository, 2017

Barcelona GSE Masters Thesis which generalizes RandNLA to GLMs.

Recommended citation: Lange, Robert Tjarko. (2017). "Randomized Numerical Linear Algebra for Generalized Linear Models with Big Datasets." UPF/UAB Public Online Repository.

Action Grammars: A Grammar Induction-Based Method for Learning Temporally-Extended Actions

Published in Best (Applied) MAC/MRes/Specialism Project, Sponsored by Winton Capital at Imperial College London, 2018

Imperial College London Masters Thesis which provides a Context-Free Grammar based framework for learning temporal abstractions in Hierarchical Reinforcement Learning.

Recommended citation: Lange, Robert Tjarko. (2018). "Action Grammars: A Grammar Induction-Based Method for Learning Temporally-Extended Actions." Imperial College London - DoC - Best (Applied) MAC/MRes/Specialism Project 2018.

Learning not to learn: Nature versus nurture in silico

Published in -, 2020

We investigate the role of ecological uncertainty, task complexity and lifetime on the qualitative differences between meta-learning adaptation strategies.

Recommended citation: Lange, Robert Tjarko and Sprekeler, Henning. (2020). "Learning not to learn: Nature versus Nurture in Silico." arXiv. Under review..