Machine Learning for the Quantified Self: On the Art of Learning from Sensory DataSpringer, 2017 M09 28 - 231 páginas This book explains the complete loop to effectively use self-tracking data for machine learning. While it focuses on self-tracking data, the techniques explained are also applicable to sensory data in general, making it useful for a wider audience. Discussing concepts drawn from from state-of-the-art scientific literature, it illustrates the approaches using a case study of a rich self-tracking data set. Self-tracking has become part of the modern lifestyle, and the amount of data generated by these devices is so overwhelming that it is difficult to obtain useful insights from it. Luckily, in the domain of artificial intelligence there are techniques that can help out: machine-learning approaches allow this type of data to be analyzed. While there are ample books that explain machine-learning techniques, self-tracking data comes with its own difficulties that require dedicated techniques such as learning over time and across users. |
Contenido
| 1 | |
Part I Sensory Data and Features | 13 |
2 Basics of Sensory Data | 14 |
3 Handling Noise and Missing Values in Sensory Data | 25 |
4 Feature Engineering Based on Sensory Data | 51 |
Part II Learning Based on Sensory Data | 71 |
5 Clustering | 73 |
6 Mathematical Foundations for Supervised Learning | 101 |
7 Predictive Modeling without Notion of Time | 122 |
8 Predictive Modeling with Notion of Time | 167 |
9 Reinforcement Learning to Provide Feedback and Support | 203 |
Part III Discussion | 215 |
10 Discussion | 216 |
References | 223 |
| 229 | |
Otras ediciones - Ver todas
Machine Learning for the Quantified Self: On the Art of Learning from ... Mark Hoogendoorn,Burkhardt Funk Sin vista previa disponible - 2017 |
Machine Learning for the Quantified Self: On the Art of Learning from ... Mark Hoogendoorn,Burkhardt Funk Sin vista previa disponible - 2018 |
Términos y frases comunes
acc_phone_x accelerometer accelerometer data action activity level amplitude apply approach Arnold assume attributes binary Bruce calculate categorical chapter cluster complexity compute create crowdsignals dataset data points decision tree define dimension discuss distance metrics distribution echo state networks entropy Eout explain focus frequency domain heart rate hyperplane hypothesis set identify in-sample error individual input space k-means k-medoids Kalman filter label layer learning algorithms learning setup machine learning matrix mean measurements missing values model instances n-gram neurons noise optimal outlier detection output overfitting PAC learnable patterns performance predict probability quantified random forest recurrent neural network regression reinforcement learning represents self-tracking sensors sensory data shown shows smartphone specific step subset subspace supervised learning task techniques test set training data training examples training set variable variance VC dimension weights window