深度学习- Introduction..pptx

Deep Learning Lecture 1: Introduction 重庆大学软件信息服务工程实验室 余俊良 What is AI? • Artificial intelligence (AI) is a thriving field with many practical applications and active research topics. – We look to intelligent software to automate routine labor, understand speech or images, make diagnoses in medicine and support basic scientific research. – In the early days of artificial intelligence, the field rapidly tackled and solved problems that are intellectually difficult for human beings but relatively straightforward for computers—problems that can be described by a list of formal, mathematical rules. • The true challenge to artificial intelligence: solving the tasks that are easy for people to perform but hard for people to describe formally—problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images. What is AI? • A person’s everyday life requires an immense amount of knowledge about the world. Much of this knowledge is subjective and intuitive, and therefore difficult to articulate in a formal way. • Several artificial intelligence projects have sought to hard- code knowledge about the world in formal languages. – using logical inference rules, people struggle to devise formal rules with enough complexity to accurately describe the world. It is an unwieldy process. Machine Learning • The difficulties faced by systems relying on hard-coded knowledge suggest that AI systems need the ability to acquire their own knowledge, by extracting patterns from raw data. This capability is known as machine learning. • The performance of these simple machine learning algorithms depends heavily on the representation of the data they are given. Representation Learning • Many artificial intelligence tasks can be solved by designing the right set of features to extract for that task, then providing these features to a simple machine learning algorithm. • However, for many tasks, it is difficult to know what features should be extracted. – Image recognition • One solution to this problem is to use machine learning to discover not only the mapping from representation to output but also the representation itself. This approach is known as representation learning. Representation Learning • A representation learning algorithm can discover a good set of features for a simple task in minutes, or a complex task in hours to months. Manually designing features for a complex task requires a great deal of human time and effort; it can take decades for an entire community of researchers. – The quintessential example of a representation learning algorithm is the autoencoder. • Learned representations often result in much better perform- ance than can be obtained with hand-designed representatio- ns. They also allow AI systems to rapidly adapt to new tasks, with minimal human intervention. Representation Learning • When designing features or algorithms for learning features, our goal is usually to separate the that explain the observed factors of variation data. Such factors are often not quantities that are directly observed. Instead, they may exist either as unobserved objects or unobserved forces in the physical world that affect observable quantities. They may also exist as constructs in the human mind that provide useful simplifying explanations or inferred causes of the observed data. They can be thought of as concepts or abstractions that help us make sense of the rich variability in the data. Representation Learning • Sometimes, it can be very difficult to extract such high-level, abstract features from raw data. – such as a speaker’s accent, can be identified only using sophisticated, nearly human-level understanding of the data. • When it is nearly as difficult to obtain a representation as to solve the original problem, representation learning does not, at first glance, seem to help us. Deep Learning • Deep learning solves this central problem in representation learning by introducing representations that are expressed in terms of other, simpler representations. Deep learning allows the computer to build complex concepts out of simpler concepts. • Figure in next page shows how a deep learning system can represent the concept of an image of a person by combining simpler concepts, such as corners and contours, which are in turn defined in terms of edges. The function mapping from a set of pixels to an object identity is very complicated. Learning or evaluating this mapping seems insurmountable if tackled directly. Deep learning resolves this difficulty by breaking the desired complicated mapping into a series of nested simple mappings, each described by a different layer of the model. Deep Learning • The quintessential example of a deep learning model is the feed-forward deep network or multilayer perceptron (MLP). A multilayer perceptron is just a mathematical function mapp- ing some set of input values to output values. The function is formed by composing many simpl。