AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

On Scrambling Phenomena for Randomly Initialized Recurrent Networks

Vaggos Chatziafratis, Ioannis Panageas, Clayton Sanford, Stelios Andrew Stavroulakis

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: RNN training dynamics and gradients · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use He initialization for the recurrent weightsRNN(k, σ²) · RNN(k, σ²)probability of Li-Yorke chaos: at least δImproved
Reduce weight variance to 1/(4k log k)RNN(k, σ²) · RNN(k, σ²)probability of Li-Yorke chaos: at most 1/kHurt
Increase weight scale to σ = ω(1)RNN(k, σ²) · RNN(k, σ²)probability of Li-Yorke chaos: lim_{k → ∞} Pr{f_k is Li-Yorke chaotic} = 1Improved
Use weights with variance ω(1/k)RNN(k, σ²) · RNN(k, σ²)probability of period 3: lim_{k → ∞} Pr{f_k is 3-periodic} = 1Improved
Use He initializationRNN(k, σ²) · RNN feedback iterationsnumber of linear regions: exponential in the number t of feedback iterationsImproved
Reduce weight variance to 1/(4k log k)RNN(k, σ²) · RNN(k, σ²)probability of having no fixed points: ≥ 1-1/kImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy