B26
Tensor networks and multiscale representations
Which correlations survive when a tensor-network representation is truncated?

IV.09 / AI
How much of the change in image recognition can be attributed to training data, accelerators and architecture?
The 2012 ImageNet paper connected a deep convolutional architecture with a large supervised image benchmark and a practical training system. Its historical significance is clearest when architecture, data, optimization, and computational resources are examined together. This topic asks which changes actually improved a measured task and which lessons survive when the images or deployment conditions change.
Create a small evaluation set with ordinary images, unusual viewpoints, and altered backgrounds. Keep the labels and source records visible. Compare errors across these conditions instead of reporting only one accuracy value; a model that relies heavily on background cues may succeed on the familiar set and fail when the object remains unchanged.
Reconstruct one component comparison from the original system description and identify the additional experiment needed to isolate its contribution.
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton / NeurIPS · The 2012 convolutional-network system and ImageNet evaluation.
B26
Which correlations survive when a tensor-network representation is truncated?