online service tools

Online n-gram services:

Advertisements

Organization of Research Papers

Bibliographic online tools and services:

Video tutoroials

Learning Matlab: 02 Introduction

MATLAB Resources for Machine Learning

At the MATLAB command line, typing help followed by a function name displays documentation for a built-in function. For example, help plot will bring up help information for plotting. Further documentation can be found at the MATLAB documentation pages.

MathWorks also has a series of videos about various MATLAB features:

Introduction to MATLAB

Learning Module Learning Goals
What is MATLAB? Introduce MATLAB
The MATLAB Environment Navigate the command line, workspace, directory, and editor
MATLAB Variables Use the assignment operator to define scalar variables
MATLAB as a Calculator Perform arithmetic calculations with scalars and functions using MATLAB syntax and order of operations.
Mathematical Functions Use MATLAB variables for input and output to functions. Examples include: COS, SIN, EXP, and NTHROOT.

Vectors

Learning Module Learning Goals
Creating Vectors via Concatenation Create vectors by entering individual elements
Accessing Elements of a Vector Access specific elements of a vector
Vector Arithmetic Perform arithmetic calculations with vectors including element-wise operations
Vector Transpose Use the transpose operator to convert between row and column vectors
Creating Uniformly Spaced Vectors (The Colon Operator) Use the colon operator syntax to create vectors given the starting and ending values and the size of the interval
Creating Uniformly Spaced Vectors (The LINSPACE Function) Use the LINSPACE function to create a vector.

Visualization

Learning Module Learning Goals
Line Plots Create a line plot of a vector and customize plot markers and colors
Annotating Graphs Label axes, add a title, and add a legend to a plot

Matrices and Arrays

Learning Module Learning Goals
Creating Matrices Create matrices by directly entering scalars
Array Creation Functions Create larger matrices and vectors with built in MATLAB functions such as ZEROS and EYE
Accessing Elements of and Array Access elements of an array including entire columns or rows using row-column indexing.
Array Size and Length Use built-in functions to determine array dimensions
Concatenating Arrays Build larger arrays from smaller ones
Matrix Multiplication Perform matrix multiplication and interpret error messages related to incompatible dimensions.

Programming

Learning Module Learning Goals
Using the MATLAB Editor Write a script in the MATLAB Editor, break code into sections to execute, and find help on functions
Logical Operators Use relational and logical operators to create logical variables for program control
Conditional Data Selection Access and change elements for a vector the meet a specified criteria
If-Else Statements Use if-else statements to control which lines of code are evaluated
For Loops Repeat a sequence of commands a specified number of times
While Loops Repeat a sequence of commands while a specified condition is true
Note: all the above information is duplicated from standford machine learning course on Coursera.

Deadlocks

A deadlock situation can arise if all of the following four conditions hold simultaneously in a system:

  1. Mutual exclusion:
    at least one resource must be held in a non-shareable mode. Only one process can use the resource at any given instant of time.
  2. Hold and wait or resource holding:
    a process is currently holding at least one resource and requesting additional resources which are being held by other processes.
  3. No preemption:
    a resource can be released only voluntarily by the process holding it.
  4. Circular wait:
    a process must be waiting for a resource which is being held by another process, which in turn is waiting for the first process to release the resource. In general, there is a set of waiting processes, P = {P1, P2, …, PN}, such that P1 is waiting for a resource held by P2, P2 is waiting for a resource held by P3 and so on until PN is waiting for a resource held by P1.

These four conditions are known as the Coffman conditions from their first description in a 1971 article by Edward G. Coffman, Jr. Unfulfillment of any of these conditions is enough to preclude a deadlock from occurring.

References:

neural networks

Online resources relating to neural networks :