T-B-F

Bulusu, 2020, https://arxiv.org/pdf/2003.06979.pdf, "ANOMALOUS INSTANCE DETECTION IN DEEP LEARNING: A SURVEY",

Meinke, 2020, https://arxiv.org/abs/1909.12180, "TOWARDS NEURAL NETWORKS THAT PROVABLY KNOWWHEN THEY DON’T KNOW"

Serrà, 2020, https://arxiv.org/pdf/1909.11480.pdfn "Input complexity and out-of-distribution detection with likelihood-based generative models"

Hendrycks, 2020, https://arxiv.org/pdf/1912.02781.pdf, "AUGMIX:  A SIMPLE DATA PROCESSING METHOD  TO IMPROVE ROBUSTNESS AND UNCERTAINTY"

Liu, 2019, http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Large-Scale_Long-Tailed_Recognition_in_an_Open_World_CVPR_2019_paper.html, "Large-Scale Long-Tailed Recognition in an Open World"

T-B-F

from sklearn.metrics.pairwise import pairwise_distances
import numpy as np
import sklearn

print(sklearn.__version__)
print(np.__version__)


def posdef_check_value(d):
    d[np.isnan(d)]=0    

T-B-F

from __future__ import print_function
import numpy as np

from keras import backend as K
from keras.preprocessing import sequence
from keras.models import Model, Sequential
from keras.layers import Dense, Dropout, Embedding, LSTM, Wrapper, Input
from keras.datasets import imdb
from keras.utils.generic_utils import has_arg
import copy