关键词：机器学习；深度学习；优化算法；递归神经网络
摘 要：In my thesis I explored several techniques to improve how to eciently model signal representations and learn useful information from them. The building block of my dissertation is based on machine learning approaches to classi cation, where a (typically non-linear) function is learned from labeled examples to map from signals to some useful information (e.g. an object class present an image, or a word present in an acoustic signal).