Kaid's Blog

Introduction to support vectors In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms that analyze data used for classification and regression analysis. What are support vectors Support vectors are the data points that lie closest to the decision surface (or hyperplane) • They are the data points most difficult to classify • They have direct bearing on the optimum location of the decision surface • We can show that the optimal hyperplane stems from the function class with the lowest “capacity”= # of independent features/parameters Theoretical concept SVMs maximize the margin (Winston terminology: the ‘street’) around the separating hyperplane.  • The decision function is fully specified by a (usually very small) subset of training samples, the support vectors.  • This becomes a Quadratic programming problem that is easy to solve by standard methods Separation by Hyperplanes • Assume linear

Columnar Transposition Cipher Introduction  The columnar transposition cipher is a fairly simple, easy to implement cipher. It is a transposition cipher that follows a simple rule for mixing up the characters in the plaintext to form the ciphertext. Although weak on its own, it can be combined with other ciphers, such as a substitution cipher, the combination of which can be more difficult to break than either cipher on it's own. The  ADFGVX cipher uses a columnar transposition to greatly improve its security. Example  The key for the columnar transposition cipher is a keyword e.g.  GERMAN . The row length that is used is the same as the length of the keyword. To encrypt a piece of text, e.g. defend the east wall of the castle we write it out in a special way in a number of rows (the keyword here is  GERMAN ): G E R M A N d e f e n d t h e e a s t w a l l o f t h e c a s t l e x x In the above example, the plaintext has been padded so that it neatly fits in a