a method for deformation computation based on strain tensor elements, as an alternative to the usual way of application of gradient of displacement vector, is proposed. the method computes directly the strain tensor elements from the computed/observed changes in distances and angles between the stations of a geodetic network in two epochs of observations. displacement vector which is determined...

We propose two machine learning improvements on the existing architecture of voiceand speakerrecognition software. Where conventional systems extract two kinds of frequency data from voice recordings and use the concatenation as input, we propose two methods to allow the input vectors to interact multiplicatively. The first is a Neural Tensor Network layer under a softmax classifier, and the se...

畳み込みニューラルネットワーク（CNN）は画像など特定ドメインのデータの処理に対して高い性能を発揮することが知られている．しかしながら同時に計算能力も必要とするため，CNNの軽量化は深層学習コミュニティにおいて広く行われてきた．本稿ではテンソル分解を使ったCNNの軽量化に焦点を当てる．まずCNNのコンポーネントである畳み込み層の演算が，複数テンソル間の線形演算の表現方法であるテンソルネットワークによって記述できることを示す．次に畳み込み層の軽量化がテンソル分解によって特徴づけられること，またその分解方法もテンソルネットワークによって記述できることを示す．最後に可能な分解を探索することによって，予測精度と時間／空間複雑さのトレードオフを実験的に比較する．その結果，いくつかの非線形分解は既存の分解を凌駕することがわかった．なお，本原稿は著者らの論文1)を和訳しわかりやすく解説したものである．

Abstract With the expansion of current knowledge graph scale and increase number entities, a large graphs express same entity in different ways, so importance fusion is increasingly manifested. Traditional alignment algorithms have limited application scope low efficiency. This paper proposes an method based on neural tensor network (NtnEA), which can obtain inherent semantic information text w...

Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability to alleviate the burden of manual feature engineering. In this paper, we propose a novel neural network model for Chinese word segmentation called Max-Margin Tensor Neural Network (MMTNN). By exploiting tag embeddings and tensorbased transformation, MMTNN has the ability to ...

Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks. In this paper, we study a fundamental question that arises when designing deep network architectures: Given a target network architecture can we design a “smaller” network architecture that “approximates” the operation of the target network?...

In the machine learning fields, Recurrent Neural Network (RNN) has become a popular algorithm for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and inference. In this paper, we are trying to reduce the number of parameters and maintain the expressive power from RNN simultaneously. We utilize several tensor decom...