Up until now, we discussed neural networks with multiple layers and a wide variety of parameters to optimize. The current generation of neural networks that we often refer to as deep learning is capable of more; it is capable of learning new features automatically so that very little feature engineering and domain expertise is required. These features are created by unsupervised methods on unlabeled data later to be fed into a subsequent layer in a neural network. This method is referred to as (unsupervised) pretraining. This approach has been proven to be highly successful in image recognition, language learning, and even vanilla machine learning projects. The most important and dominant technique in recent years is called denoising autoencoders and algorithms based on Boltzmann techniques. Boltzmann machines, which were the building blocks for Deep Belief Networks (DBN), have lately fallen out of favor in the deep learning community because they turned...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from Large Scale Machine Learning with Python
Bastiaan Sjardin is a data scientist and founder with a background in artificial intelligence and mathematics. He has a MSc degree in cognitive science obtained at the University of Leiden together with on campus courses at Massachusetts Institute of Technology (MIT). In the past 5 years, he has worked on a wide range of data science and artificial intelligence projects. He is a frequent community TA at Coursera in the social network analysis course from the University of Michigan and the practical machine learning course from Johns Hopkins University. His programming languages of choice are Python and R. Currently, he is the cofounder of Quandbee (http://www.quandbee.com/), a company providing machine learning and artificial intelligence applications at scale.
Read more about Bastiaan Sjardin
Alberto Boschetti is a data scientist with expertise in signal processing and statistics. He holds a Ph.D. in telecommunication engineering and currently lives and works in London. In his work projects, he faces challenges ranging from natural language processing (NLP) and behavioral analysis to machine learning and distributed processing. He is very passionate about his job and always tries to stay updated about the latest developments in data science technologies, attending meet-ups, conferences, and other events.
Read more about Alberto Boschetti
Unlock this book and the full library FREE for 7 days
Authors (2)
Bastiaan Sjardin is a data scientist and founder with a background in artificial intelligence and mathematics. He has a MSc degree in cognitive science obtained at the University of Leiden together with on campus courses at Massachusetts Institute of Technology (MIT). In the past 5 years, he has worked on a wide range of data science and artificial intelligence projects. He is a frequent community TA at Coursera in the social network analysis course from the University of Michigan and the practical machine learning course from Johns Hopkins University. His programming languages of choice are Python and R. Currently, he is the cofounder of Quandbee (http://www.quandbee.com/), a company providing machine learning and artificial intelligence applications at scale.
Read more about Bastiaan Sjardin
Alberto Boschetti is a data scientist with expertise in signal processing and statistics. He holds a Ph.D. in telecommunication engineering and currently lives and works in London. In his work projects, he faces challenges ranging from natural language processing (NLP) and behavioral analysis to machine learning and distributed processing. He is very passionate about his job and always tries to stay updated about the latest developments in data science technologies, attending meet-ups, conferences, and other events.
Read more about Alberto Boschetti