Bài giảng Máy học nâng cao: Deep learning an introduction - Trịnh Tấn Đạt

Bài giảng "Máy học nâng cao: Deep learning an introduction" cung cấp cho người học các kiến thức: Introduction, applications, convolutional neural networks and recurrent neural networks, hardware and software. Mời các bạn cùng tham khảo nội dung chi tiết.
Nội dung trích xuất từ tài liệu:
Bài giảng Máy học nâng cao: Deep learning an introduction - Trịnh Tấn ĐạtTrịnh Tấn ĐạtKhoa CNTT – Đại Học Sài GònEmail: trinhtandat@sgu.edu.vnWebsite: https://sites.google.com/site/ttdat88/Contents Introduction Applications Convolutional Neural Networks vs. Recurrent Neural Networks Hardware and SoftwareIntroduction to Deep LearningIntroduction to Deep LearningWhy Deep Learning? Machine learning is a field of computer science that gives computers the ability to learn without being explicitly programmed Methods that can learn from and make predictions on dataWhy Deep Learning?Why Deep Learning?Why Deep Learning? Can we learn the underlying features directly from data?Why Deep Learning? ML vs. Deep Learning: Most machine learning methods work well because of human-designed representations and input features ML becomes just optimizing weights to best make a final predictionWhy Deep Learning? Challenges of ML:  Relevant data acquisition  Data preprocessing  Feature selection  Model selection: simplicity versus complexity  Result interpretation.What is Deep Learning (DL)? A machine learning subfield of learning representations of data. Exceptional effective at learning patterns. Deep learning algorithms attempt to learn (multiple levels of) representation by using a hierarchy of multiple layers If you provide the system tons of information, it begins to understand it and respond in useful ways.Why is DL useful? Manually designed features are often over-specified, incomplete and take a long time to design and validate Learned Features are easy to adapt, fast to learn Deep learning provides a very flexible, (almost?) universal, learnable framework for representing world, visual and linguistic information. Can learn both unsupervised and supervised Utilize large amounts of training data In ~2010 DL started outperforming other ML techniques first in speech and vision, then NLPWhy is DL useful?Why is DL useful?Why Now?The Perceptron: Forward Propagation Neural Network Architectures Back Propagation for Weight UpdateImportance of Activation Functions The purpose of activation functions is to introduce non-linearities into the networkIntroduction to Deep Learning Activation functionIntroduction to Deep Learning Neural Network Adjustements