Cover image

What a Spiking Network Learns to Forget

TL;DR for operators Making a classifier more resistant to corrupted or manipulated inputs can reduce its accuracy on ordinary ones. On CIFAR-10, Spiking Conditional Information Bottleneck (SCIB) raises accuracy under a specified iterative adversarial attack from 0.78% to 47.58%, while clean accuracy falls from 92.94% to 89.69% (four timesteps; PGD at 4/255, Section 5.4, Table 2).1 SCIB achieves this by training a spike-based neural network to retain information useful for classification while compressing additional input variation within each class, without changing its neuronal dynamics. It also leads 15 of 18 tested environmental-noise configurations, though robustness gains vary by disturbance. On CIFAR-100, clean accuracy drops by 9.07 percentage points in a four-timestep comparison. The reported 24.9% inference-energy reduction is an analytical estimate, not a hardware measurement. For edge-AI operators, the decision is whether improved robustness against expected disturbances justifies the clean-accuracy loss and whether projected computational savings translate into actual deployment benefits. ...

November 13, 2026 · 8 min · Zelina
Cover image

Compress the Features, Keep the Timeline: SGWIB’s Case for Structure-Aware Video Bottlenecks

TL;DR for operators If a video-ranking model must compress a long sequence before deciding which moments deserve attention, the central design question is not simply how much information to remove. Compression can also change the relationships among temporal segments, and those relationships are part of what a ranking system uses to decide that one moment matters more than another. ...

October 4, 2026 · 7 min · Zelina
Cover image

Noise-Canceling Finance: How the Information Bottleneck Tames Overfitting in Asset Pricing

TL;DR for operators Most quant teams already know the awkward truth: adding model capacity often makes the research backtest look smarter while making the deployed model less useful. The interesting part of Che Sun’s paper is not that it adds another neural network to asset pricing. We have enough of those. The useful move is more surgical: it asks the factor model to keep the information that helps explain returns and discard the information that merely helps memorise noisy firm characteristics.1 ...

August 1, 2025 · 16 min · Zelina