Activation Functions

博客中列举了四种激活函数,分别是sigmoid,tanh,Relu,Leaky Relu;对于初学机器学习是基本够用的在线新回归使用sigmoid做非线性变换讲y值映射到0-1空间;

NameFunctionDerivative
sigmoidg(z) = \frac{1}{1+(e^{-z})}g(z)(1-g(z))
tanhtanh(z)1-(tanh(z))^2
0, if z < 0
Relumax(0,z)1, if z>0
undefined,if z = 0
0.01, if z<0
Leaky Relumax(0.01z,z)1, if z>0
undefine, if z = 0

2022/7/8

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
I am an AI language model and cannot create images directly. However, I can describe the structure of the DeepNeuralNet class in a text format, which you can use as a guide to drawing the network structure. The structure looks like this: 1. Input Layer: This is where the network receives user and item inputs. Each input goes through an embedding layer, with n_users and n_items as the number of embeddings, and n_factors as the size of the embeddings. 2. Concatenation Layer: The output of the user and item embedding layers is concatenated, resulting in a tensor of shape (batch_size, n_factors*2). 3. Fully Connected Hidden Layers: The concatenated tensor is then passed through a series of fully connected layers. In your case, you have two hidden layers of sizes 64 and 32. Each layer is defined as a Linear layer with a specified number of input and output features, and these layers are stored in a ModuleList (fc_layers). 4. Dropout Layer: After passing through the hidden layers, the network goes through a dropout layer with probability 0.2. This randomly sets some elements to zero during training to prevent overfitting. 5. Output Layer: After the dropout layer, the network passes through another Linear layer, which reduces the tensor's dimension to 1. 6. Sigmoid Activation: Finally, the output goes through a sigmoid activation function, which squashes the output value between 0 and 1. The sigmoid activation is applied to make the output ready for predicting ratings or binary outcomes such as preferences. To draw the structure, you can use rectangles to represent the Linear layers and circles for activation functions. Label the rectangles with the number of input and output features, and label the circles with the activation function's name. Connect the rectangles with lines to visualize the information flow.用图展示这个网络层·
06-08

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值