Deepseek R1, DNNs, feature transfer with Richard Aragon

References;
1.DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning arxiv.org/pdf/...
2.Distilling the Knowledge in a Neural Network arxiv.org/pdf/...
3. Deep Neural Networks are Easily Fooled:
High Confidence Predictions for Unrecognizable Images arxiv.org/pdf/...
4. How transferable are features in deep neural
networks? proceedings.ne...
5. CNN Features off-the-shelf: an Astounding Baseline for Recognition www.cv-foundat...