Fat details
Fat introduction
Fat (Federated AI Technology Enabler) is an open source project initiated by the AI Department of Weizhong bank, which aims to provide a secure computing framework to support the federal AI ecosystem. It implements a secure computing protocol based on homomorphic encryption and multiparty computing (MPC). It supports the secur ...
Added by eXpertPHP on Sun, 19 Sep 2021 22:37:29 +0300
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