Hyperparameters are parameters of neural networks other than w and b, including learning rate, depth of layer, size of each layer and so on. Compared to model parameters w and b, hyperparameters are determined entirely by ourselves. Tuning a model is to find better hyperparameters.
Dive into deep learning (D2L) is a online deep learning course by Mu Li. In this course, Mu Li teaches the basic concept of DL and usage of pytorch. This post includes the environment configuration in windows, introduction of this course and some basic concept about matrix derivative.
This post records the experimental process of labs of Unsupervised Learning, Recommenders, Reinforcement Learning by Andrew Ng and some bugs that may be encountered under Windows.
This post records the experimental process of labs of Advanced Learning Algorithms by Andrew Ng and some bugs that may be encountered under Windows.
This post records the experimental process of labs of Supervised Machine Learning - Regression and Classification by Andrew Ng and some bugs that may be encountered under Windows.
Reinforcement learning is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize cumulative reward. This post includes the course notes of reinforcement learning course by Andrew Ng.
A recommender system is a subclass of information filtering system that provides suggestions for items that are most pertinent to a particular user. This post includes the course notes of recommender system course by Andrew Ng.
Unsupervised learning is a type of algorithm that learns patterns or data groupings from unlabeled data without the need for human intervention. This post includes the course notes of unsupervised learning course by Andrew Ng.
Decision trees are decision support hierarchical model that use tree model to make judgment or decision. Decision trees are commonly used in decision analysis, but are also a popular tool in machine learning.
When building a machine learning system, there are actually a series of processes, namely, the full cycle of the machine learning project. Training models is just one step of the cycle.