Study

Chapter 18, 19, 20

  •   0%
  •  0     0     0

  • Networks of interconnected nodes based on the interconnections between neurons in the human brain. The system is able to think like a human using these neural networks, and its performance improves with more data.
    Artificial Neural Networks
  • Describe A* algorithm
    A* algorithm – an algorithm that finds the shortest route between nodes or vertices but uses an additional heuristic approach to achieve better performance than
  • ... - a method of searching an ordered list by testing the value of the middle item in the list and rejecting the half of the list that does not contain the required value.
    Binary Search
  • statements of facts and rules together with a mechanism for setting goals in the form of a query.
    Declarative programming
  • a method of sorting data in an array into alphabetical or numerical order by placing each item in turn in the correct position in the sorted list.
    Insertion Sort
  • time complexity of binary search
    O(logN)
  • Method used in artificial neural networks to calculate error gradients so that actual node/neuron weightings can be adjusted to improve the performance of the model.
    Back Propogation
  • System which is able to identify hidden patterns from input data – the system is not trained on the ‘right’ answer
    Unsupervised learning
  • – a template defining the methods and data of a certain type of object.
    Class
  • Statistical measure used to make predictions from data by finding learning relationships between the inputs and outputs.
    Regression
  • – process in which the methods and data from one class, a superclass or base
    Inheritance
  • – a mathematical notation used to describe the performance or complexity of an algorithm
    Big O notation
  • feature of object-oriented programming that allows methods to be redefined for derived classes
    Polymorphism
  • programming instructions that use the computer’s basic instruction set.
    Low-level programming
  • An occurrence of an object during the execution of a program.
    Instance
  • Systems that learn without being programmed to learn.
    Machine Learning
  • Machines that think in a way similar to the human brain. They handle huge amounts of data using artificial neural networks.
    Deep Learning
  • System which is given no training – learns on basis of ‘reward and punishment’.
    Reinforcement Learning
  • Describe Dijkstra’s algorithm
    Dijkstra’s algorithm – an algorithm that finds the shortest path between two nodes or vertices in a graph/network.
  • Time complexity of a linear search
    O(N)
  • – a programming methodology that uses selfcontained objects, which contain programming statements (methods) and data, and which communicate with each other.
    OOP
  • process of putting data and methods together as a single unit, a class.
    Encapsulation
  • an instance of a class that is self-contained and includes data and methods.
    Object
  • a hierarchical data structure in which each parent node can have a maximum of two child nodes.
    Binary Tree
  • programming paradigm in which the steps required to execute a program are set out in the order they need to be carried out.
    Imperative Programming
  • Time complexity of bubble, insertion sort
    O(N^2)
  • – a process using a function or procedure that is defined in terms of itself and calls itself.
    Recursion
  • System which is able to predict future outcomes based on past data. It requires both input and output values to be used in the training process.
    Supervised Learning