Toward Interpretable Deep Generative Models via Causal Representation Learning
通过因果表征学习构建可解释的深度生成模型
Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art performance across wide-ranging domains. These methods’ surprising performance is due in part to their ability to learn implicit “representations” of complex, multi-modal data. Unfortunately, deep neural networks are notoriously black boxes that obscure these representations, making them difficult to…