Browsing: Yannic Kilcher
This casting of our field in terms of ideological narrow-sighted group-think is disgusting. Keep Science about ideas! Links: YouTube: Twitter:…
Classic RL “stops” the world whenever the Agent computes a new action. This paper considers a more realistic scenario where…
The cross-entropy loss has been the default in deep learning for the last few years for supervised learning. This paper…
A calculation of the memory requirements of the Longformer. Original video: Paper: Links: YouTube: Twitter: BitChute: Minds: source
Schmidhuber writes up a critique of Hinton receiving the Honda Price… AND HINTON REPLIES! Schmidhuber’s Blog Entry: Hinton’s Reply: Thumbnail…
Has the world overfitted to ImageNet? What if we collect another dataset in exactly the same fashion? This paper gives…
Are virtual conferences good or bad? What’s missing? How do we go forward? Pictures from here: Links: YouTube: Twitter: BitChute:…
This paper dives into the intrinsics of the Lottery Ticket Hypothesis and attempts to shine some light on what’s important…
Hail the AI Tax Collector! This very visual framework has RL Agents maximize their coins in a tiny world through…
Here’s a lazy way to separate computation and subsequent analysis in a notebook without the overhead of manually saving local…