You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert
強化学習の創始者の一人であり、この分野を長年にわたってリードしてきたUniversity of Alberta教授のRichard Sutton氏が「The Bitter Lesson」(苦い教訓)というタイトルで記事を投稿した(図1)1)。以下にその内容を簡単にまとめる。 この70年間のAI研究で得られた最も大きな教訓は、計算能力を活かした汎用の手法が最終的には最も有効であったということである。この背景にあるのはムーアの法則として知られる計算能力の指数的な性能向上である。一般にAIの研究では、エージェントの計算能力は固定だと考える。この場合、AIの性能を向上させるためには人間のドメイン知識をシステムに埋め込むしかない。しかし、一般的な研究プロジェクトの期間より長い期間でみると、計算能力の向上を活かした汎用の手法が最終的に大きな差をつけて有効だとわかる。 例として、チェスでは1997年に米
Knowledge and reasoning in GPT modelsHere’s an example to illustrate this point. GPT-4 is the most advanced model on the market today. Its reasoning capabilities are so good that it can get a 5 on the AP Bio exam. But if I ask it who I am it says the following: That’s close to being right except for one big problem…I’m the co-founder of a few companies, but neither of them are Superhuman or Reify.
マジレスされてチビッた.こりゃGoogleさんもビビるわけだ. ぼく: How were you implemented? Is it deep learning-based? ChatGPT: I am a language model called GPT-3 (Generative Pre-trained Transformer 3) that was developed by OpenAI. It is a deep learning-based model that uses a type of neural network called a transformer, which was trained on a large dataset of text to learn patterns of language. GPT-3 is trained using a techni
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く