Placeholder Image

字幕表 動画を再生する

  • SERENA AMMIRATI: Looking at this book page by page

  • and trying to decipher, read, and transcribe whatever is

  • there takes an enormous amount of time.

  • It would require an army of paleographers.

  • ELENA NIEDDU: What I am excited the most about machine learning

  • is that it enabled us to solve problems that up to 10,

  • 15 years ago we thought unsolvable.

  • ELENA NIEDDU: Before using any kind of machine learning model,

  • we needed to collect data first.

  • You have thousands of images of dogs and cats in the internet,

  • but there's very little images of ancient manuscripts.

  • We built our own custom web application for crowdsourcing.

  • And we involved high school students to collect the data.

  • I didn't know much about machine learning in general.

  • But I found it very easy to create a TensorFlow

  • environment.

  • When we were trying to figure out

  • which model worked best for us, Keras was the best solution.

  • The production model runs on TensorFlow layers, an estimator

  • interface.

  • We experimented with binary classification,

  • with fully connected networks.

  • And finally, we moved to convolutional neural network

  • and multiclass classification.

  • ELENA NIEDDU: When it comes to recognizing single characters,

  • we can get 95% average accuracy.

  • SERENA AMMIRATI: This will have an enormous impact.

  • In a short period of time, we will

  • have a massive quantity of historical information

  • available.

  • ELENA NIEDDU: I just think solving problems is fun.

  • It's a game against myself, and how good I can do.

SERENA AMMIRATI: Looking at this book page by page


動画の操作 ここで「動画」の調整と「字幕」の表示を設定することができます

B1 中級

TensorFlowを利用して:機械学習を利用した中世のテキストの転記を支援する古書家の支援 (Powered by TensorFlow: helping paleographers transcribe medieval text using machine learning)

  • 0 0
    林宜悉 に公開 2021 年 01 月 14 日