Intelligent Robot

Implementation of neural networks - ASL Data preparation import pandas as pd import numpy as np train_df = pd.read_csv("data/sign_mnist_train.csv") valid_df = pd.read_csv("data/sign_mnist_valid.csv") train_df.head() y_train = train_df['label'] y_valid = valid_df['label'] del train_df['label'] del valid_df['label'] x_train = train_df.values x_valid = valid_df.values print(x_train.shape) print(x_v..

Implementation of neural network - MNIST Test on Google colab import torch from torch.utils.data import Dataset from torchvision import datasets from torchvision.transforms import ToTensor import matplotlib.pyplot as plt device = torch.device("cuda:0") Data preparation train_data = datasets.MNIST(root="data", train=True, download=True, transform=ToTensor()) test_data = datasets.MNIST(root="data"..

Categorization of machine learning Supervised Learning Given a set of labeled example, D={(xt,yt)}Nt=1 , learn a mapping f:X→Y which minimizes L(Y^=f(X),Y) Classification The desired outputs yt are discrete class labels (categorical information) The goal is to classify new inputs correctly Regression The desired outputs yt are continuous values The goal is to predict the output values for new in..

* 참고 : 이 글은 colab의 .ipynb 파일을 통하여 실험하였습니다. 1. Deep Learning Basics Deep Learning Learn hierarchical representations and the prediction model simultaneously, that are optimal for given task. Deep in the sense that it has multiple levels of non-linear feature transformations. Artificial Neural Networks Systems of interconnected neurons which learns parameters that non-linearly converts some inputs..

딥러닝에서 python을 이용하여 다양하게 프로그램을 할 수 있지만 Class를 만들어 관리하는 것이 간편하고 중요하다. 이에 대하여 간단히 알아본다. * 참고 : 이 글은 colab의 .ipynb 파일을 통하여 실험하였습니다. Class and objects Class Class is a frame which can create identical things Object Things generated by a class Features of Python Class In object-oriented programming, the composition of the program is made around objects A class is a frame that defines the properties an..