From Sensory Substitution to Decision Transformers, Persistent Evolution Strategies and Sharpness-Aware Minimization — Welcome to the December edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of the month…

From Auto-ML to Vision Transformer Training & Representations and Catastrophic Fisher Explosion — Welcome to the September edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of the month…

From Optimizer Benchmarks to Network Dissection, Vision Transformers & Lottery Subspaces — Welcome to the August edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of the month…

From Large Scale Deep RL to Adversarial Robustness, SimCLR-v2 & Learning Neural Network Spaces — Welcome to the July edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of the month…

From Bayesian Neural Networks to Self-Supervised Learning, Class Selectivity and Core Ideas from Statistics — Welcome to the June edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of the month…

From Asymmetric Self-Play for Robotics to Generalization of Networks, Gated Linear Networks & Meta-Learned Update Rules — Welcome to the end of April edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of…

From Meta-Gradients to Clockwork VAEs, a Global Workspace Theory for Neural Networks and the Edge of Training Stability — Welcome to the April edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is this series about? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of the month…

From Synthetic Gradients to Capsule Networks, Conservation Laws for Network Training & Multi-Agent Generative Models — Welcome to the end of February edition of the ‚Machine-Learning-Collage‘ series, where I provide an overview of the different Deep Learning research streams. So what is an ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. Every single week. At the end of…

Scaling CMA-ES with the Power of vmap and jit — “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…