1. Line regression 1.1 Ordinary Least Squares (OLS) Perspective 1.1.1 Model Representation: The linear regression model is represented as: \hat{Y} = X
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Implement average pooling through a convolution. import torch import torch.nn.functio
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Assume that we have two convolution kernels of size k_1 and k_2, respectively (with n
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Given the final code example in this section with kernel size (3,5), padding (0,1), a
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Construct an image X with diagonal edges. import torch def corr2d(X,K): h,w = K.
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Assume that the size of the convolution kernel is \Delta=0. Show that in
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Even if there is no need to deploy trained models to a different device, what are the
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Design a layer that takes an input and computes a tensor reduction, i.e., it returns
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. What happens if you specify the input dimensions to the first layer but not to subseq
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. Use the NestMLP model defined in Section 6.1 and access the parameters of the various
github: https://github.com/pandalabme/d2l/tree/main/exercises 1. What kinds of problems will occur if you change MySequential to store modules in a Py
