분류 전체보기(327)
-
4. Binary Classification
Notation: - (x,y) - m training example : (x1,y1), (x2,y2), ... , (xm,ym) - 이때 X : all training set training set은 각 train sample을 column방향으로 stack. 따라서 X.shape : (n(x), m) - n(x) 는 input xm의 feature dimension Y 또한 column 방향으로 stack. 따라서 Y.shape : (1,m) binary classification : input X -> output y(0 or 1)
2023.09.08 -
3. Why is Deep Learning taking off?
Why is deep learning suddenly working so well? - over the last 10 years maybe is that for a lot of problems we went from having a relatively small amout of data. but now, we have a fairly large amout of data and all of this was thanks to the digitization of a society. for hit this very high level of performance ten wyou need two things. 1. size of Neural Network 2. enough data(=labeled data) if ..
2023.09.05 -
2. Supervised Learning with Neural Networks
Supervised Learning : 지도학습 - want to learn function mapping 'x' to 'y' Structured Data : 정형 데이터(Databases of data) UnStructured Data : 비정형 데이터(audio, image, text etc..)
2023.09.05 -
1. What is a Neural Network?
예시 : 집 값 예측 input : x layer : unit output : y(=price) layer에 사용될 수 있는 function - ex) ReLU(Rectified Linear Unit) x -> max(0,x) x : house size, number of bedrooms, zip code, wealth etc.. layer : family size(=related with house size, number of bedrooms), school quality(=related with zip code, wealth) y : price
2023.09.05 -
텐서플로우(Tensorflow) gpu 사용 가능 여부 확인하기
from tensorflow.python.client import device_lib device_lib.list_local_devices() [name: "/device:CPU:0" device_type: "CPU" memory_limit: 268435456 locality { } incarnation: 10360034786306285900 xla_global_id: -1, name: "/device:GPU:0" device_type: "GPU" memory_limit: 7787773952 locality { bus_id: 1 links { } } ]
2023.08.23 -
텐서플로우(Tensorflow), 케라스(Keras) 버전 확인
import tensorflow as tf print(tf.__version__) import keras print(keras.__version__)
2023.07.30