Python Artificial Intelligence Projects for Beginners

C
clustering method  
convolutional neural network (CNN)  
, 
D
decision trees
   about  
, 
, 
, 
   used, for predicting student performance data 
, 
, 
, 
, 
, 
, 
deep learning methods
   about  
   convolutions  
, 
, 
, 
, 
, 
, 
   pooling  
, 
, 
, 
, 
, 
, 
Doc2Vec
   about  
, 
   document vector  
, 
document vector  
, 
H
handwritten mathematical symbols
   identifying, with CNNs  
, 
, 
, 
, 
,
, 
, 
, 
, 
hyperparameters  
K
K-fold cross validation  
M
Mel-frequency cepstral coefficients (MFCC)  
N
neural networks
   about  
, 
, 
   feed-forward  
, 
, 
, 
, 
, 
, 
, 
, 
,
, 
   genre of song, identifying  
, 
, 
   used, for revising spam detector  
, 
, 
,
, 
, 
O
one-hot encoding  
P
Pipeline  
predictions  
R
random forests
   about  
, 
, 
   confusion matrix, creating for data  
, 
, 
,
, 
, 
   usage  
   used, for predicting bird species  
, 
, 
, 
,
, 
, 
, 

---

S
Skip-gram  
spam detector
   revising, neural networks used  
, 
, 
, 
,
, 
student performance dataset
   reference link  
supervised learning  
T
term frequency inverse document frequency (TF-
IDF)  
text classification
   about  
   bag of words  
, 
, 
   machine learning techniques  
, 
U
user reviews
   negative sentiments, detecting  
, 
, 
, 
,
   positive sentiments, detecting  
, 
, 
, 
, 
V
voting  
W
Word2Vec models
   about  
, 
, 
   Doc2Vec  
, 
Y
YouTube comment spam
   detecting  
, 
, 
, 
, 
, 
, 
, 
, 
, 

---

Document Outline

• Cover
• Title Page
• Copyright and Credits
• Packt Upsell
• Contributors
• Table of Contents
• Preface
• Chapter 1: Building Your Own Prediction Models
  • Classification overview and evaluation techniques
    • Evaluation
  • Decision trees
  • Common APIs for scikit-learn classifiers
  • Prediction involving decision trees and student performance data
  • Summary
• Chapter 2: Prediction with Random Forests
  • Random forests
    • Usage of random forest
  • Predicting bird species with random forests
    • Making a confusion matrix for the data
  • Summary
• Chapter 3: Applications for Comment Classification
  • Text classification
    • Machine learning techniques
    • Bag of words
  • Detecting YouTube comment spam
  • Word2Vec models
    • Doc2Vec
      • Document vector
  • Detecting positive or negative sentiments in user reviews
  • Summary
• Chapter 4: Neural Networks
  • Understanding neural networks
    • Feed-forward neural networks
  • Identifying the genre of a song with neural networks
  • Revising the spam detector to use neural networks
  • Summary
• Chapter 5: Deep Learning
  • Deep learning methods
    • Convolutions and pooling
  • Identifying handwritten mathematical symbols with CNNs
  • Revisiting the bird species identifier to use images
  • Summary
• Other Books You May Enjoy
• Index