Все доклады последней ИИшницы "NeurIPS 2022" можно посмотреть в плейлисте по ссылке, а также отдельными видео:
🟤 "Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes"
🟤 "HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks"
🟤 "Wasserstein Iterative Networks for Barycenter Estimation"
🟤 "Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?"
🟤 "Nonparametric Uncertainty Quantification for Single Deterministic Neural Network"
🟤 "Smoothed Embeddings for Certified Few-Shot Learning"
🟤 "TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning"
🟤 "Recurrent Memory Transformer"
🟤 "Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes"
Как обещали, делимся презентациями спикеров 🖇
Как обещали, делимся презентациями спикеров 🖇