A New Life

1. 준비 기간: 2023.05.23~2023.06.30 이 자격증을 준비한 이유는 딱히 없습니다. 이거 하나 딴다고 업계에서 인정해주는거도 아니고, 시험 내용은 이미 보통의 데이터 사이언티스트라면 대강 알고있는 것이라 엄청나게 유익한 것도 아니고, 시험응시료도 비싼데 굳이 왜?하는 분위기이지만 제가 자격증 공부를 한지 오래되어서 공부하는 방법을 감을 못잡고 있어서 정신 좀 차리려고 웜업 겸 따기로 했어요. 아무것도 못하고 축 쳐져 있는 것보다 쓸모없는 자격증이라도 따는게 제 인생에 도움이 되겠지 싶어서요. 그래서 자격증 관련해서 서치해보니 코세라 강연을 쭉 한 번 들으면 무리없이 딸 수 있다고 해서 한 번 쭉 듣고 문제 풀어보고 시험을 쳤습니다. 과정이 일주일이면 충분히 들을 수 있을만한 강의였어요. ..

Week 4: Using real world data Welcome! So far you have worked exclusively with generated data. This time you will be using the Daily Minimum Temperatures in Melbourne dataset which contains data of the daily minimum temperatures recorded in Melbourne from 1981 to 1990. In addition to be using Tensorflow's layers for processing sequence data such as Recurrent layers or LSTMs you will also use Con..

Week 3: Using RNNs to predict time series Welcome! In the previous assignment you used a vanilla deep neural network to create forecasts for generated time series. This time you will be using Tensorflow's layers for processing sequence data such as Recurrent layers or LSTMs to see how these two approaches compare. Let's get started! import tensorflow as tf import numpy as np import matplotlib.py..

Week 2: Predicting time series Welcome! In the previous assignment you got some exposure to working with time series data, but you didn't use machine learning techniques for your forecasts. This week you will be using a deep neural network to create forecasts to see how this technique compares with the ones you already tried out. Once again all of the data is going to be generated. Let's get sta..

Week 1: Working with time series Welcome! In this assignment you will be working with time series data. All of the data is going to be generated and you will implement several functions to split the data, create forecasts and evaluate the quality of those forecasts. Let's get started! import numpy as np import tensorflow as tf from tensorflow import keras import matplotlib.pyplot as plt The next..

Week 4: Predicting the next word Welcome to this assignment! During this week you saw how to create a model that will predict the next word in a text sequence, now you will implement such model and train it using a corpus of Shakespeare's sonnets, while also creating some helper functions to pre-process the data. Let's get started! NOTE: To prevent errors from the autograder, please avoid editin..

Week 3: Exploring Overfitting in NLP Welcome to this assignment! During this week you saw different ways to handle sequence-like data. You saw how some Keras' layers such as GRU, Conv and LSTM can be used to tackle problems in this space. Now you will put this knowledge into practice by creating a model architecture that does not overfit. For this assignment you will be using a variation of the ..

Week 2: Diving deeper into the BBC News archive Welcome! In this assignment you will be revisiting the BBC News Classification Dataset, which contains 2225 examples of news articles with their respective labels. This time you will not only work with the tokenization process but you will also create a classifier using specialized layers for text data such as Embedding and GlobalAveragePooling1D. ..

Week 1: Explore the BBC News archive Welcome! In this assignment you will be working with a variation of the BBC News Classification Dataset, which contains 2225 examples of news articles with their respective categories (labels). Let's get started! import csv from tensorflow.keras.preprocessing.text import Tokenizer from tensorflow.keras.preprocessing.sequence import pad_sequences Begin by look..

Week 4: Multi-class Classification Welcome to this assignment! In this exercise, you will get a chance to work on a multi-class classification problem. You will be using the Sign Language MNIST dataset, which contains 28x28 images of hands depicting the 26 letters of the english alphabet. You will need to pre-process the data so that it can be fed into your convolutional neural network to correc..

Week 3: Transfer Learning Welcome to this assignment! This week, you are going to use a technique called Transfer Learning in which you utilize an already trained network to help you solve a similar problem to the one it was originally trained to solve. Let's get started! NOTE: To prevent errors from the autograder, please avoid editing or deleting non-graded cells in this notebook . Please only..

Week 2: Tackle Overfitting with Data Augmentation Welcome to this assignment! As in the previous week, you will be using the famous cats vs dogs dataset to train a model that can classify images of dogs from images of cats. For this, you will create your own Convolutional Neural Network in Tensorflow and leverage Keras' image preprocessing utilities, more so this time around since Keras provides..