Machine learning principle and practice | PCA Dimensionality Reduction Practice

%matplotlib inline import matplotlib.pyplot as plt import numpy as np 1. PCA introduction 1.1 concept Thought: dots = np.array([[1, 1.5], [2, 1.5], [3, 3.6], [4, 3.2], [5, 5.5]]) def cross_point(x0, y0): """ 1. line1: y = x 2. line2: y = -x + b => x = b/2 3. [x0, y0] is in line2 => b = x0 + y0 => x1 = b/2 = ...

Added by IanMartins on Tue, 14 Sep 2021 03:33:54 +0300

Second job: multi-layer perceptron

1, Linear neural network (1) Linear regression 1. Linear model The linear model is regarded as a single-layer neural network. 2. Loss function The loss function can quantify the difference between the actual value and the predicted value of the target.   3. Analytical solution     4. Optimization method: small batch grad ...

Added by cyberlew15 on Mon, 13 Sep 2021 04:38:22 +0300

pytorch | Dragon Boat Festival learning notes

pytorch learning import torch import numpy as np a=torch.rand(4,3,28,28) #torch.rand(batch_size, channel, row, column) a[0].shape #batch_ shape with size = 0: torch.Size([3, 28, 28]) a[0,0].shape #batch_ shape with size = 0 and channel 0: torch.Size([28, 28]) a[0,0,2,4] #batch_size=0, pixels in Row 2 and column 4 on the 0 ...

Added by tacojohn on Sat, 04 Sep 2021 02:45:12 +0300