background preloader

Reads

Facebook Twitter

Class Diagram Relationships in UML with ExamplesCreately Blog. Explicit cookie consent. New sorts of transistors can eke out a few more iterations of Moore’s law, but they will get increasingly expensive THANKS to the exponential power of Moore’s law, the electronic components that run modern computers vastly outnumber all the leaves on the Earth’s trees.

Explicit cookie consent

Computer Programming: From Machine Language to Artificial Intelligence. Takeaway: As computing power has increased, programming languages have evolved to take advantage of enhanced computing resources.

Computer Programming: From Machine Language to Artificial Intelligence

Programming languages were used even before computers were invented. Natural language processing. Natural language processing (NLP) is a field of computer science, artificial intelligence, and computational linguistics concerned with the interactions between computers and human (natural) languages.

Natural language processing

As such, NLP is related to the area of human–computer interaction. Many challenges in NLP involve natural language understanding, that is, enabling computers to derive meaning from human or natural language input, and others involve natural language generation. History[edit] The Mind Project: Curriculum. AI, Robotics & Computational Models This module provides an introduction to artificial neural nets with a working network that can solve X-OR problem.

The Mind Project: Curriculum

Chain codes are a kind of computer program that can be used to represent the shape of objects. Seven hands-on activities show how to write simple chain codes and explain their application to computer vision. Natural language processing. Gold Mine or Blind Alley? Functional Programming for Big Data & Machine Learning. Functional programming is touted as a solution for big data problems.

Gold Mine or Blind Alley? Functional Programming for Big Data & Machine Learning

PhysicsGirl.com. The Mind Project: Curriculum. The XOR Problem and Solution - The Mind Project. An architectural Solution to the XOR Problem Now here's a problem.

The XOR Problem and Solution - The Mind Project

Let's try to build a neural network that will produce the following truth table, called the 'exclusive or' or 'XOR' (either A or B but not both): In order to solve the problem, we need to introduce a new layer into our neural networks. This layer, often called the 'hidden layer', allows the network to create and maintain internal representations of the input. Here's is a network with a hidden layer that will produce the XOR truth table above: XOR Network From Rumelhart, et al. 1986, p 64. Fair enough. Neural networks and deep learning. One of the most striking facts about neural networks is that they can compute any function at all.

Neural networks and deep learning

That is, suppose someone hands you some complicated, wiggly function, f(x): No matter what the function, there is guaranteed to be a neural network so that for every possible input, x, the value f(x) (or some close approximation) is output from the network, e.g. Neuroplasticity. Contrary to conventional thought as expressed in this diagram, brain functions are not confined to certain fixed locations.

Neuroplasticity

Neuroplasticity, also known as brain plasticity, is an umbrella term that describes lasting change to the brain throughout an animal's life course. The term gained prominence in the latter half of the 20th century, when new research[1] showed many aspects of the brain remain changeable (or "plastic") even into adulthood.[2] This notion contrasts with the previous scientific consensus that the brain develops during a critical period in early childhood, then remains relatively unchangeable (or "static") afterward.[3] Marvin Minsky's Home Page. MIT Media Lab and MIT AI Lab Professor of Media Arts and Sciences, MIT Professor of E.E.C.S., M.I.Tminsky at media.mit.edu.

Marvin Minsky's Home Page

Psychology. Psychology is an academic and applied discipline that involves the scientific study of mental functions and behaviors.[1][2] Psychology has the immediate goal of understanding individuals and groups by both establishing general principles and researching specific cases,[3][4] and by many accounts it ultimately aims to benefit society.[5][6] In this field, a professional practitioner or researcher is called a psychologist and can be classified as a social, behavioral, or cognitive scientist.

Psychology

Psychologists attempt to understand the role of mental functions in individual and social behavior, while also exploring the physiological and biological processes that underlie cognitive functions and behaviors. While psychological knowledge is often applied to the assessment and treatment of mental health problems, it is also directed towards understanding and solving problems in many different spheres of human activity. Etymology History. Human echolocation. Human echolocation is the ability of humans to detect objects in their environment by sensing echoes from those objects, by actively creating sounds – for example, by tapping their canes, lightly stomping their foot, snapping their fingers, or making clicking noises with their mouths – people trained to orient by echolocation can interpret the sound waves reflected by nearby objects, accurately identifying their location and size. This ability is used by some blind people for acoustic wayfinding, or navigating within their environment using auditory rather than visual cues.

It is similar in principle to active sonar and to animal echolocation, which is employed by bats, dolphins and toothed whales to find prey. Background[edit] Mechanics[edit] Google Brain. Google Brain is a deep learning research project at Google. History[edit] In June 2012, the New York Times reported that a cluster of 16,000 computers dedicated to mimicking some aspects of human brain activity had successfully trained itself to recognize a cat based on 10 million digital images taken from YouTube videos.[1] The story was also covered by National Public Radio[2] and SmartPlanet.[3] Meet the man building an AI that mimics our neocortex – and could kill off neural networks. The Man Behind the Google Brain: Andrew Ng and the Quest for the New AI.