Corpus ID: 51971247

Dropout during inference as a model for neurological degeneration in an image captioning network

@article{Li2018DropoutDI,
  title={Dropout during inference as a model for neurological degeneration in an image captioning network},
  author={Bai Li and Ran Zhang and Frank Rudzicz},
  journal={ArXiv},
  year={2018},
  volume={abs/1808.03747}
}
We replicate a variation of the image captioning architecture by Vinyals et al. (2015), then introduce dropout during inference mode to simulate the effects of neurodegenerative diseases like Alzheimer's disease (AD) and Wernicke's aphasia (WA). We evaluate the effects of dropout on language production by measuring the KL-divergence of word frequency distributions and other linguistic metrics as dropout is added. We find that the generated sentences most closely approximate the word frequency… Expand

References

SHOWING 1-10 OF 27 REFERENCES
Show and tell: A neural image caption generator
TLDR
This paper presents a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. Expand
Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
TLDR
The m-RNN model directly models the probability distribution of generating a word given previous words and an image, and achieves significant performance improvement over the state-of-the-art methods which directly optimize the ranking objective function for retrieval. Expand
Linguistic Features Identify Alzheimer's Disease in Narrative Speech.
BACKGROUND Although memory impairment is the main symptom of Alzheimer's disease (AD), language impairment can be an important marker. Relatively few studies of language in AD quantify theExpand
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
TLDR
An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. Expand
Detecting subtle spontaneous language decline in early Alzheimer’s disease with a picture description task
TLDR
Prospective assessment of spontaneous language skills with a picture description task is useful to detect those subtle spontaneous language impairments caused by AD even at an early stage of the disease. Expand
Recurrent Neural Network Regularization
TLDR
This paper shows how to correctly apply dropout to LSTMs, and shows that it substantially reduces overfitting on a variety of tasks. Expand
Language performance in Alzheimer's disease and mild cognitive impairment: A comparative review
  • V. Taler, N. Phillips
  • Psychology, Medicine
  • Journal of clinical and experimental neuropsychology
  • 2008
TLDR
This work reviews language performance in MCI, compares these findings to those seen in AD, and identifies the primary issues in understanding language performance and selecting tasks with diagnostic and prognostic value. Expand
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
TLDR
Qualitatively, the proposed RNN Encoder‐Decoder model learns a semantically and syntactically meaningful representation of linguistic phrases. Expand
A linguistic analysis of fluent aphasia
Abstract Fluent aphasia is a general term for those posterior aphasic syndromes which involve little or no motor difficulties and which exhibit rather normal rates of speech output. This paper is aExpand
AphasiaBank: Methods for studying discourse
TLDR
AphasiaBank will provide researchers with an important new tool in the study of aphasia and will allow researchers access to a large, shared database that can facilitate hypothesis testing and increase methodological replicability, precision, and transparency. Expand
...
1
2
3
...