I also began to expand my learning scope through
Posted: Thu Jan 02, 2025 10:30 am
Learning is always a tiring thing, and I personally particularly like divergent learning. So although I have learned a lot of new content eagerly in the past few days, I have kept procrastinating on taking notes and have never put anything down.
Simply put, in addition to watching Andrew Ng's videos, on the terms algeria phone number data in them. I learned about terms such as DNN/CNN/RNN, and then checked frameworks such as TensorFlow/Caffee. Since I currently love the Swift language, I also read some Core ML and Vision documents on the Apple Developer website. But so far, this knowledge has not been truly put into paper. So the more information I see, the more confused I am. In the end, I decided that I still need to focus and start with the basics.
What is Machine Learning
Wikipedia describes machine learning as follows:
There are several definitions of machine learning:
Machine learning is a science of artificial intelligence. The main research object of this field is artificial intelligence, especially how to improve the performance of specific algorithms through empirical learning.
Machine learning is the study of computer algorithms that improve automatically through experience.
Machine learning is the use of data or past experience to optimize the performance criteria of a computer program.
An often cited English definition is: A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
This definition seems to make "machine learning" clear, but it seems to be vague and not particularly memorable. As a former developer, I am going to simplify this definition. Machine learning is the science of letting computers find patterns from a pile of disorganized data and form algorithms.
In the past, when writing code, the algorithm was always fixed by the programmer according to the needs, and then the user input, such as mouse, touch, keyboard input, etc., was converted into text, animation or voice on the screen according to certain rules for output. However, when faced with some particularly complex problems, such as voice, image recognition, and unmanned driving, they may be powerless. And these areas are precisely where machine learning can play its strengths.
Classification of Machine Learning
Machine learning is mainly divided into supervised learning and unsupervised learning. The main difference lies in whether the elements in the training set are labeled by someone.
Supervised Learning
The definition on Wikipedia is as follows:
Supervised learning learns a function from a given training data set, and when new data arrives, the result can be predicted based on this function. The training set for supervised learning requires input and output, or features and targets. The targets in the training set are labeled by humans. Common supervised learning algorithms include regression analysis and statistical classification.
In supervised learning, we have some existing data, and these data are the "right answers" that objectively exist in reality. And these data have various labels.
Simply put, in addition to watching Andrew Ng's videos, on the terms algeria phone number data in them. I learned about terms such as DNN/CNN/RNN, and then checked frameworks such as TensorFlow/Caffee. Since I currently love the Swift language, I also read some Core ML and Vision documents on the Apple Developer website. But so far, this knowledge has not been truly put into paper. So the more information I see, the more confused I am. In the end, I decided that I still need to focus and start with the basics.
What is Machine Learning
Wikipedia describes machine learning as follows:
There are several definitions of machine learning:
Machine learning is a science of artificial intelligence. The main research object of this field is artificial intelligence, especially how to improve the performance of specific algorithms through empirical learning.
Machine learning is the study of computer algorithms that improve automatically through experience.
Machine learning is the use of data or past experience to optimize the performance criteria of a computer program.
An often cited English definition is: A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
This definition seems to make "machine learning" clear, but it seems to be vague and not particularly memorable. As a former developer, I am going to simplify this definition. Machine learning is the science of letting computers find patterns from a pile of disorganized data and form algorithms.
In the past, when writing code, the algorithm was always fixed by the programmer according to the needs, and then the user input, such as mouse, touch, keyboard input, etc., was converted into text, animation or voice on the screen according to certain rules for output. However, when faced with some particularly complex problems, such as voice, image recognition, and unmanned driving, they may be powerless. And these areas are precisely where machine learning can play its strengths.
Classification of Machine Learning
Machine learning is mainly divided into supervised learning and unsupervised learning. The main difference lies in whether the elements in the training set are labeled by someone.
Supervised Learning
The definition on Wikipedia is as follows:
Supervised learning learns a function from a given training data set, and when new data arrives, the result can be predicted based on this function. The training set for supervised learning requires input and output, or features and targets. The targets in the training set are labeled by humans. Common supervised learning algorithms include regression analysis and statistical classification.
In supervised learning, we have some existing data, and these data are the "right answers" that objectively exist in reality. And these data have various labels.