Understanding Recurrent Neural State Using Memory Signatures
نویسندگان
چکیده
We demonstrate a network visualization technique to analyze the recurrent state inside the LSTMs/GRUs used commonly in language and acoustic models. Interpreting intermediate state and network activations inside end-to-end models remains an open challenge. Our method allows users to understand exactly how much and what history is encoded inside recurrent state in grapheme sequence models. Our procedure trains multiple decoders that predict prior input history. Compiling results from these decoders, a user can obtain a signature of the recurrent kernel that characterizes its memory behavior. We demonstrate this method’s usefulness in revealing information divergence in the bases of recurrent factorized kernels, visualizing the character-level differences between the memory of n-gram and recurrent language models, and extracting knowledge of history encoded in the layers of grapheme-based end-to-end ASR networks.
منابع مشابه
Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
Recurrent neural networks, and in particular long short-term memory networks (LSTMs), are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better understanding these models have studied the changes in hidden state representations over time and noticed some interpretable patterns but also sig...
متن کاملEnd-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
Spoken language understanding (SLU) is a core component of a spoken dialogue system. In the traditional architecture of dialogue systems, the SLU component treats each utterance independent of each other, and then the following components aggregate the multi-turn information in the separate phases. However, there are two challenges: 1) errors from previous turns may be propagated and then degra...
متن کاملCriticality meets learning: Criticality signatures in a self-organizing recurrent neural network
Many experiments have suggested that the brain operates close to a critical state, based on signatures of criticality such as power-law distributed neuronal avalanches. In neural network models, criticality is a dynamical state that maximizes information processing capacities, e.g. sensitivity to input, dynamical range and storage capacity, which makes it a favorable candidate state for brain f...
متن کاملDialogue State Tracking using Long Short Term Memory Neural Networks
We propose a dialogue state tracker based on long short term memory (LSTM) neural networks. LSTM is an extension of a recurrent neural network (RNN), which can better consider distant dependencies in sequential input. We construct a LSTM network that receives utterances of dialogue participants as input, and outputs the dialogue state of the current utterance. The input utterances are separated...
متن کاملRecurrent Memory Networks for Language Modeling
Recurrent Neural Networks (RNNs) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent Memory Network (RMN), a novel RNN architecture, that not only amplifies the power of RNN but also facilitates our understanding of its internal functioning and ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1802.03816 شماره
صفحات -
تاریخ انتشار 2018