딥러닝

• CNN has great success in computer vision applications, especially in image classification,based on its shared weights using Convolution and translat

Feedforward neural network (FFNN) as MLP• Information only flows in one direction.• No sense of time or memory for previous data.Recurrent neural netw

CNN-LSTM model for Image Captioning > Image Captioning은 이미지를 언어로 설명하는 작업이다. > CNN as an encoder is used to learn features in images. LSTM as a decode

Auto-Encoder (AE)• Auto-Encoder is an unsupervised learning for data reconstruction by encoding-decoding.Specifically, its bottleneck network forces a

Variational Auto-Encoder (VAE)• AE encoder directly produces a latent vector z (single value for each attribute).Then, AE decoder takes these values t

Generative Adversarial Network (GAN)• GenerativeLearn a generative model• AdversarialTrained in an adversarial setting: generator G and discriminator

basic machine learning concepts mathematical notations principles of learning linear regression overfitting regularization Vectors, Matrices and Norms

출처 CS231n Python, Numpy Tutorial

Matplotlib은 MATLAB과 유사한 플로팅 시스템을 제공하는 플로팅 라이브러리입니다. 특히, matplotlib.pyplot 모듈은 데이터를 시각적으로 나타내는 데 사용되며, 이를 통해 그래프를 그리고 스타일을 지정할 수 있습니다. 아래에서 Matplotlib의