개인 공부
-
Representation Learning - greedy layer-wise unsupervised pretraining개인 공부/딥러닝 기초 개념 2023. 9. 3. 16:42
Unsupervised learning played a key historical role in the revival of deep neural networks, enabling researchers for the first time to train a deep supervised network without requiring architectural specialization like convolution or recurrence. We call this procedure unsupervised pretraining, or more precisely, greedy layer-wise unsupervised pretraining. This procedure is a canonical example of ..
-
Representation Learning - Introduction개인 공부/딥러닝 기초 개념 2023. 8. 26. 17:09
reference : Deep Learning (Ian Goodfellow) Generally speaking, a good representation is one that makes a subsequent learning task easier. The choice of representation will usually depend on the choice of the subsequent learning task. We can think of feedforward networks trained by supervised learning as performing a kind of representation learning. Specifically, the last layer of the network is ..
-
Eigendecomposition개인 공부/딥러닝 기초 개념 2023. 8. 26. 15:11
선형대수 많이 까먹어서.. 기억을 되짚어보기 위해 올립니다. reference : Deep learning (Ian Goodfellow, Yoshua Bengio, Aaron Courville)EigendecompositionEigendecomposition means that we decompose a matrix into a set of eigenvectors and eigenvalues. An eigen vector of a square matrix A is a nonzero vector $v$ such that multipication by A alters only the scale of $v$ $Av = \lambda v$ the scalar $\lambda$ is known as eigenva..