[過去ﾛｸﾞ] 【統計分析】機械学習・データマイニング20 (1002ﾚｽ)

【統計分析】機械学習・データマイニング20 http://mevius.5ch.net/test/read.cgi/tech/1533635797/

上下前次1-新
通常表示 512ﾊﾞｲﾄ分割 ﾚｽ栞
抽出解除 ﾚｽ栞

---

このｽﾚｯﾄﾞは過去ﾛｸﾞ倉庫に格納されています｡
次ｽﾚ検索 歴削→次ｽﾚ 栞削→次ｽﾚ 過去ﾛｸﾞﾒﾆｭｰ

---

718: デフォルトの名無しさん (ﾜｯﾁｮｲ d980-A6IM) [] 2018/10/07(日) 21:24:55.65 ID:mIq+f5AO0 https://arxiv.org/pdf/1312.4400.pdf > 3.2 Global Average Pooling > ・・・ > However, the fully connected layers are prone to overfitting, thus hampering the generalization ability > of the overall network. Dropout is proposed by Hinton et al. [5] as a regularizer which randomly > sets half of the activations to the fully connected layers to zero during training. It has improved the > generalization ability and largely prevents overfitting [4]. > In this paper, we propose another strategy called global average pooling to replace the traditional > fully connected layers in CNN. http://mevius.5ch.net/test/read.cgi/tech/1533635797/718

719: デフォルトの名無しさん (ｱｳｱｳｶｰ Sa0a-bfG9) [sage] 2018/10/07(日) 21:52:22.17 ID:7A10mDJxa >>718 全結合いれたら汎化性が落ちるから他の方法でってことか ありがとう http://mevius.5ch.net/test/read.cgi/tech/1533635797/719

---

ﾒﾓ帳

(0/65535文字)

---

上下前次1-新書関写板覧索設栞歴

---

ｽﾚ情報 赤ﾚｽ抽出 画像ﾚｽ抽出 歴の未読ｽﾚ

---

Google検索

Wikipedia

---

ぬこの手 ぬこTOP 0.052s