Machine learning (ML)        i.          Types and approaches of ML (1200 words and should include: supervised, semi-supervised,

Machine learning (ML)

      
i.         
Types and approaches of ML (1200 words and should
include: supervised, semi-supervised, unsupervised learning, reinforcement
learning, self-learning, feature learning, spare dictionary learning, deep
learning, rule-based learning including learning classifier systems and
inductive logic programming)

     
ii.         
ML Models and algorithms (1000 words and should include:
Artificial neural networks, K- nearest neighbor (KNN), decision trees, random
forest, support-vector machines, linear regression analysis, Bayesian networks,
genetic algorithms, linear classifier, hierarchical clustering, Cortial
learning algorithm, anomaly detection)

    iii.         
Hierarchical temporal memory (HTM): (500 words and should
include HTM History and component crucial facts)

    iv.         
ML Models assessment measures (500 words)

     
v.         
ML in the context of smart transport (650 words and should
include: its types or approaches, used algorithms, and its role in
relation to anomaly detection and traffic congestion)