khirotaka

set number
imap <c-j> <esc>


"シンタックスハイライトの設定
syntax on


"タブ の大きさをスペース 4つ分に設定
set expandtab

khirotaka

• Discovering Semantic Motifs in the Time Series

• Time Series Mining in the Face of Fast Moving Streams using a Learned Approximate Matrix Profile

• Discovering Subdimensional Motifs of Different Length in Large-Scale Multivariate Time Series

• Exploiting Time Series Consensus Motifs to Find Structure in Time Series Sets

• A Wasserstein Subsequence Kernel for Time Series

  • GitHub

• MTEX-CNN: Multivariate Time series EXplanations for Predictions with Convolutional Neural Networks

khirotaka

見出し1

見出し2

見出し3

見出し4

見出し5

見出し6

---

hello,

khirotaka

import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader

import sdc.datasets.uci as uci

khirotaka

FROM pytorch/pytorch:0.4.1-cuda9-cudnn7-devel

RUN apt-get update \
    && apt-get install -y  --no-install-recommends \
    build-essential \
    vim \
    python-pil \
    python-matplotlib \
    python-pygraphviz \
    default-jdk \

khirotaka

NIPS 2017

Attentional Pooling for Action Recognition

• Paper
• Code

VideoCapsuleNet: A Simplified Network for Action Detection

• Paper
• Code

khirotaka

import SwiftUI
import PlaygroundSupport

/*:
 # Example of SwiftUI Page Transition
 
 Run on Swift Playground (iPad)
 
 nest is too deep...
 */

khirotaka

,reals_0,reals_1,reals_2,reals_3,reals_4,reals_5,reals_6,reals_7,reals_8,reals_9,reals_10,reals_11,reals_12,reals_13,reals_14,reals_15,reals_16,reals_17,reals_18,reals_19,reals_20,reals_21,reals_22,reals_23,reals_24,reals_25,reals_26,reals_27,reals_28,reals_29,reals_30,reals_31,reals_32,reals_33,reals_34,reals_35,reals_36,reals_37,reals_38,reals_39,reals_40,reals_41,reals_42,reals_43,reals_44,reals_45,reals_46,reals_47,reals_48,reals_49,imags_0,imags_1,imags_2,imags_3,imags_4,imags_5,imags_6,imags_7,imags_8,imags_9,imags_10,imags_11,imags_12,imags_13,imags_14,imags_15,imags_16,imags_17,imags_18,imags_19,imags_20,imags_21,imags_22,imags_23,imags_24,imags_25,imags_26,imags_27,imags_28,imags_29,imags_30,imags_31,imags_32,imags_33,imags_34,imags_35,imags_36,imags_37,imags_38,imags_39,imags_40,imags_41,imags_42,imags_43,imags_44,imags_45,imags_46,imags_47,imags_48,imags_49
0,1.0,0.9988944140783094,0.9996443157199939,0.9994913534405574,0.9989981660069169,0.9999788370353451,0.9988261796241285,0.9997799955037704,0.99

khirotaka

IJCAI 2018

---

GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction

• Paper
• Code

Abstract

Numerous sensors have been deployed in different geospatial locations to continuously and cooperatively monitor the surrounding environment, such as the air quality. These sensors generate multiple geo-sensory time series, with spatial correlations between their readings. Forecasting geo-sensory time series is of great importance yet very challenging as it is affected by many complex factors, i.e., dynamic spatio-temporal correlations and external factors. In this paper, we predict the readings of a geo-sensor over several future hours by using a multi-level attention-based recurrent neural network that considers multiple sensors' readings, meteorological data, and spatial data. More specifically, our model consists of two major parts: 1) a multi-level attention mechanism to model the dynamic spatio-te

khirotaka

AAAI 2019

---

Adversarial Unsupervised Representation Learning for Activity Time-Series

• Paper

Abstract

Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions. Being able to proactively screen and monitor such chronic conditions would be a big step forward for overall health.