Wordlist for playing Skribbl.io using Machine Learning terminology

machine_learning_wordlist.txt

accuracy
activation function
active learning
artificial intelligence
AUC
augmentation
augmented reality
backpropagation
bag of words
batch normalization
Bayesian neural network
bias
binary classification
binning
boosting
bounding box
broadcasting
bucketing
categorical data
centroid
class
classification
clustering
collaborative filtering
computer vision
confirmation bias
confusion matrix
continuous feature
convergence
convex function
convolutional layer
convolutional neural network
cross entropy
cross validation
dataframe
datapoint
decision boundary
decision tree
deep neural network
dense layer
discrete feature
discriminator
downsampling
dropout regularization
eager execution
embeddings
ensemble model
environment
epoch
false negative
false positive
feature engineering
feature extraction
feature vector
feedforward
generative adversarial network
generator
gradient
gradient descent
ground truth
hashing
heuristic
hidden layer
image recognition
imbalanced dataset
input layer
instance
keras
kernel
k means
k medians
k nearest neighbors
l1 regularization
l2 regularization
label
lambda
layer
learning rate
least squares regression
linear regression
logistic regression
long short term memory
loss
machine learning
matrix factorization
mean squared error
model
natural language processing
negative class
neural network
neuron
normalization
numpy
one hot encoding
online learning
output layer
overfitting
pandas
parameter
partial derivative
perceptron
performance
pipeline
pooling
positive class
precision
preprocessing
prior
q learning
random forest
recall
rectified linear unit
recurrent neural network
regression model
regularization
reinforcement learning
reward
root directory
scikit learn
sigmoid function
softmax
tensor
tensorflow
training set
true negative
true positive
underfitting
unsupervised learning
vanishing gradient problem

skribbl_format.txt

accuracy,activation function,active learning,artificial intelligence,AUC,augmentation,augmented reality,backpropagation,bag of words,batch normalization,Bayesian neural network,bias,binary classification,binning,boosting,bounding box,broadcasting,bucketing,categorical data,centroid,class,classification,clustering,collaborative filtering,computer vision,confirmation bias,confusion matrix,continuous feature,convergence,convex function,convolutional layer,convolutional neural network,cross entropy,cross validation,dataframe,datapoint,decision boundary,decision tree,deep neural network,dense layer,discrete feature,discriminator,downsampling,dropout regularization,eager execution,embeddings,ensemble model,environment,epoch,false negative,false positive,feature engineering,feature extraction,feature vector,feedforward,generative adversarial network,generator,gradient,gradient descent,ground truth,hashing,heuristic,hidden layer,image recognition,imbalanced dataset,input layer,instance,keras,kernel,k means,k medians,k nearest neighbors,l1 regularization,l2 regularization,label,lambda,layer,learning rate,least squares regression,linear regression,logistic regression,long short term memory,loss,machine learning,matrix factorization,mean squared error,model,natural language processing,negative class,neural network,neuron,normalization,numpy,one hot encoding,online learning,output layer,overfitting,pandas,parameter,partial derivative,perceptron,performance,pipeline,pooling,positive class,precision,preprocessing,prior,q learning,random forest,recall,rectified linear unit,recurrent neural network,regression model,regularization,reinforcement learning,reward,root directory,scikit learn,sigmoid function,softmax,tensor,tensorflow,training set,true negative,true positive,underfitting,unsupervised learning,vanishing gradient problem