Auto-encoders are a form of dimensionality reduction technique. When they are used in this manner, they mathematically and conceptually have similarities to other dimensionality reduction techniques such as PCA. Auto-encoders consist of two parts: an encoder which creates a representation of the data, and a decoder which tries to reproduce or predict the inputs. Thus, the hidden layers and neurons are not maps between an input and some other outcome, but are self (auto)-encoding. Given sufficient complexity, auto-encoders can simply learn the identity function, and the hidden neurons will exactly mirror the raw data, resulting in no meaningful benefit. Similarly, in PCA, using all the principal components also provides no benefit. Therefore, the best auto-encoder is not necessarily the most accurate one, but one that reveals some meaningful structure...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from R Deep Learning Essentials. - Second Edition
Mark Hodnett is a data scientist with over 20 years of industry experience in software development, business intelligence systems, and data science. He has worked in a variety of industries, including CRM systems, retail loyalty, IoT systems, and accountancy. He holds a master's in data science and an MBA. He works in Cork, Ireland, as a senior data scientist with AltViz.
Read more about Mark Hodnett
Joshua F. Wiley is a lecturer at Monash University, conducting quantitative research on sleep, stress, and health. He earned his Ph.D. from the University of California, Los Angeles and completed postdoctoral training in primary care and prevention. In statistics and data science, Joshua focuses on biostatistics and is interested in reproducible research and graphical displays of data and statistical models. He develops or co-develops a number of R packages including Varian, a package to conduct Bayesian scale-location structural equation models, and MplusAutomation, a popular package that links R to the commercial Mplus software.
Read more about Joshua F. Wiley
Unlock this book and the full library FREE for 7 days
Authors (2)
Mark Hodnett is a data scientist with over 20 years of industry experience in software development, business intelligence systems, and data science. He has worked in a variety of industries, including CRM systems, retail loyalty, IoT systems, and accountancy. He holds a master's in data science and an MBA. He works in Cork, Ireland, as a senior data scientist with AltViz.
Read more about Mark Hodnett
Joshua F. Wiley is a lecturer at Monash University, conducting quantitative research on sleep, stress, and health. He earned his Ph.D. from the University of California, Los Angeles and completed postdoctoral training in primary care and prevention. In statistics and data science, Joshua focuses on biostatistics and is interested in reproducible research and graphical displays of data and statistical models. He develops or co-develops a number of R packages including Varian, a package to conduct Bayesian scale-location structural equation models, and MplusAutomation, a popular package that links R to the commercial Mplus software.
Read more about Joshua F. Wiley