Deep Learning With Dynamic Computation Graphs (ICLR 2017)
On distributed systems broadly defined and other curiosities. The opinions on this site are my own. This is a paper by Google that is under submission to ICLR 2017. Here is the OpenReview link for the paper. The paper pdf as well as paper reviews are openly available there. What a concept! This paper was of interest to me because I wanted to learn about dynamic computation graphs. Unfortunately al
Deep Learning with Dynamic Computation Graphs
Neural networks that compute over graph structures are a natural fit for problems in a variety of domains, including natural language (parse trees) and cheminformatics (molecular graphs). However, since the computation graph has a different shape and size for every input, such networks do not directly support batched training or inference. They are also difficult to implement in popular deep learn
TensorFlow Foldについて
Googleが、TensorFlow Foldというライブラリーを発表しました。 "Announcing TensorFlow Fold: Deep Learning With Dynamic Computation Graphs" (論文は、こちら) この図の意味について簡単に説明したいと思います、 "computer scientists love "という文は、文字列あるいはwordのSepquence として見ることができます。普通のRNNやLSTMでは、こうしたSequenceとして入力を受け付けます。 ただ、先のSequenceは、文法的な構造を持っています。"computer scientists"が主語（節）で、"love"が動詞、"putting data in trees"が目的語（節）です。
1
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
