Tags: Allen

Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...
Shortcomings of Deep Learning

Shortcomings of Deep Learning

Current Deep Learning successes such as AlphaGo rely on massive amount of labeled data, which is easy to get in games, but often hard in other contexts. You can't play 20 questions wi...