What is machine learning?

  • 2021-02-21
  • 0

Machine learning is to find functions automatically.For example, speech recognition, image recognition, playing go, dialogue system…



2.binary classification

output is yes or no

3.multiclass classification

Let the machine do multiple choice questions.The machine selects the correct one in the options.


Produce structured complex things.Like images,sentences created like a human.

How to tell the machine what kind of function to look for?

1.supervised learning

labeled data.Need to give the machine some labeled data for training.

2.function loss
Judge whether the function is good or bad. The basic idea is as follows: First, the image is given to the function for output, and the output result is compared with the label. The proportion of the correct answer is related to the quality of the function.

The smaller the LOSS, the closer to the function we need to find. Next, the machine will automatically select the function with the lowest LOSS value.

3.reinforcement learning

The result will allow the machine to evaluate previous decisions.And alpha go both use supervised learning and reinforcement learning.

4.unsupervised learning

unlabeled data.What can machine learn from unlabeled data.

5.Function search range

Linear,Network Architecture,like RNN and CNN.

6.Function search method

gradient descent.PyTorch.


1.Explainable AI.

Tell us why this result is output.

2.Adversarial Attack

Deliberately modify the input data to confuse the machine, resulting in an error in its selection function.

3.Network compression

Compress the data input and put it on the phone.

4.anomaly detection

Enter something completely different,Can you let the machine know that ‘i don’t know’?

5.Transfer Learning

Training data AND testing data.learn by analogy.BUT when testing data totally different with the training data, what tragety will machine choose.

6.Meta learning

let machine can learn by itself! learning algorithmn.

Can you make the machine smarter?create learning algorithmn.

7.Life-long learning

Machine life-long learning.Continuous learning.