Basic IT Semester1 2014 ID5731301058 : Artificial neural network

Artificial neural network

From Wikipedia, the free encyclopedia

"Neural network" redirects here. For networks of living neurons, see Biological neural network. For the journal, see Neural Networks (journal).

In machine learning and related fields, artificial neural networks (ANNs) are computational models inspired by an animal's central nervous systems (in particular the brain) which is capable of machine learning as well as pattern recognition. Artificial neural networks are generally presented as systems of interconnected "neurons" which can compute values from inputs.

An artificial neural network is an interconnected group of nodes, akin to the vast network of neurons in a brain. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one neuron to the input of another.

For example, a neural network for handwriting recognition is defined by a set of input neurons which may be activated by the pixels of an input image. After being weighted and transformed by a function (determined by the network's designer), the activations of these neurons are then passed on to other neurons. This process is repeated until finally, an output neuron is activated. This determines which character was read.

Like other machine learning methods - systems that learn from data - neural networks have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including computer vision and speech recognition.

History

Warren McCulloch and Walter Pitts (1943) created a computational model for neural networks based on mathematics and algorithms. They called this modelthreshold logic. The model paved the way for neural network research to split into two distinct approaches. One approach focused on biological processes in the brain and the other focused on the application of neural networks to artificial intelligence.

In the late 1940s psychologist Donald Hebb created a hypothesis of learning based on the mechanism of neural plasticity that is now known as Hebbian learning. Hebbian learning is considered to be a 'typical' unsupervised learning rule and its later variants were early models for long term potentiation. These ideas started being applied to computational models in 1948 with Turing's B-type machines.

Farley and Wesley A. Clark (1954) first used computational machines, then called calculators, to simulate a Hebbian network at MIT. Other neural network computational machines were created by Rochester, Holland, Habit, and Duda (1956).

Frank Rosenblatt (1958) created the perceptron, an algorithm for pattern recognition based on a two-layer learning computer network using simple addition and subtraction. With mathematical notation, Rosenblatt also described circuitry not in the basic perceptron, such as the exclusive-or circuit, a circuit whose mathematical computation could not be processed until after the backpropagation algorithm was created by Paul Werbos(1975).

Neural network research stagnated after the publication of machine learning research by Marvin Minsky and Seymour Papert (1969). They discovered two key issues with the computational machines that processed neural networks. The first issue was that single-layer neural networks were incapable of processing the exclusive-or circuit. The second significant issue was that computers were not sophisticated enough to effectively handle the long run time required by large neural networks. Neural network research slowed until computers achieved greater processing power. Also key later advances was the backpropagation algorithm which effectively solved the exclusive-or problem (Werbos 1975).

The parallel distributed processing of the mid-1980s became popular under the name connectionism. The text by David E. Rumelhart and James McClelland (1986) provided a full exposition on the use of connectionism in computers to simulate neural processes.

Neural networks, as used in artificial intelligence, have traditionally been viewed as simplified models of neural processing in the brain, even though the relation between this model and brain biological architecture is debated, as it is not clear to what degree artificial neural networks mirror brain function.

In the 1990s, neural networks were overtaken in popularity in machine learning by support vector machines and other, much simpler methods such as linear classifiers. Renewed interest in neural nets was sparked in the 2000s by the advent of deep learning.

References

 McCulloch, Warren; Walter Pitts (1943). "A Logical Calculus of Ideas Immanent in Nervous Activity". Bulletin of Mathematical Biophysics 5 (4): 115–133. doi:10.1007/BF02478259

IT WORKSHOP SEMESTER 1 2014 ID5731301058 : My self and IT learning domain

My self and IT learning domain

Basic IT Semester1 2014 ID5731301058 : Role and Impact of ICT to The raise of ISIS.

The raise of ISIS

At the start of classes one year ago, I had to explain to my students why the United States appeared to be on the verge of going to war against the Syrian government. At the beginning of this semester, exactly one year later, I’m having to explain to my students why the United States may be on the verge of going to war against Syrian rebels.

Already, U.S. planes and missiles have been attacking the so-called Islamic State (ISIS) forces in northern Iraq. Given the threat of a genocidal campaign against Yazidis and other minorities and the risks of ISIS control expanding into the Kurdish region, even some of those normally averse to unilateral U.S. military intervention abroad have considered it the lesser of two evils.

Within days, however, there were already indications of “mission creep,” as what had been officially declared an exclusively defensive mission turned offensive when the United States provided air support for Kurdish and Iraqi forces, which seized the Mosul Dam from ISIS forces.

It is not surprising, therefore, that there is skepticism regarding this use of military force. Even if one can make a convincing strategic case for such a military operation, the failure of President Obama to go before Congress for authorization of this renewed military intervention in Iraq is extremely disturbing.

Ironically, President Obama has been getting high-profile criticism from those wishing he had been more aggressive with projecting American military power. For example, in a well-publicized interview in The Atlantic, former Secretary of State Hillary Clinton blamed the rise of ISIS on Obama’s failure to sufficiently arm and support the so-called moderate rebels of the Free Syrian Army (FSA).

Such a charge defies logic, however. The FSA consists of literally hundreds of separate militia without a central command, largely composed of relatively inexperienced fighters, who would have been no match for the well-armed, experienced, disciplined fighters of ISIS, regardless of the amount of weapons the U.S. might have provided. In fact, it was an awareness of ISIS’s potential dominance of the Syrian rebel movement that served as an important reason why the Obama administration didn’t go beyond the relatively limited arming and training of a few small groups affiliated with the FSA.

Indeed, part of ISIS’s military prowess comes from weapons they captured from overrunning FSA positions and from their ranks supplemented by FSA fighters who, in the course of the three-year battle with Assad’s forces, became radicalized and switched sides.

In any case, ISIS has found an even stronger foothold in Iraq than Syria, a direct consequence of the U.S. invasion and occupation. In a profile of ISIS leader Abu Bakr al-Baghdadi, a one-time moderate Sufi turned Salafist extremist, the New York Times observed, “At every turn, Mr. Baghdadi’s rise has been shaped by the United States’ involvement in Iraq — most of the political changes that fueled his fight, or led to his promotion, were born directly from some American action.”

Almost immediately after the 2003 invasion, U.S. occupation forces systematically dismantled the country’s secular national institutions, which were quickly filled by both Sunni and Shia extremists (actions which Hillary Clinton, as a U.S. Senator, strongly supported).

The biggest division among Iraq’s Arabs, however, is not between Sunnis and Shias but between nationalist and sectarian tendencies within both communities. Under the corrupt and autocratic U.S.-backed Prime Minister Nouri al-Maliki, Shia sectarians dominated. This resulted in an initially nonviolent Sunni backlash, which was met by severe government repression. This backlash was eventually hijacked by ISIS, which rid the major Sunni-dominated cities of government control.

Whether the new Iraqi leadership will actually be willing, or able given pervasive U.S. influence, to rid the government of Shia hardliners and become more inclusive, pluralistic, and democratic remains to be seen.

Ironically, the eventual demise of ISIS will more likely stem from the group’s own fanaticism than from any action by Baghdad or the U.S. ISIS—which even the Al-Qaeda network believes is too extreme—sees not just those who aren’t Sunni Muslims as “infidels,” but anyone who doesn’t subscribe to its extremist ideology. Since almost everyone under its rule is therefore at risk, the prospects of the Iraqi and Syrian people eventually rising up against ISIS is high. In fact, Syrian nonviolent activists have already been openly defiant of ISIS.  Had the active nonviolent coalition groups in Syria received material or diplomatic support from the beginning, instead of Clinton’s “moderate” rebels, they may have been able to prevent or mitigate the rise of ISIS altogether.

Massive Western military intervention will likely create a backlash that could strengthen political support for the extremists. The United States has been bombing Iraq on and off for nearly a quarter century and things have only gotten worse, for the people of Iraq, the security interests of Iraq’s neighbors and, ultimately, for the United States. Just as Sunni tribal leaders were more effective than either U.S. forces or the Iraqi government in driving out Al-Qaeda from northwestern Iraq in 2007-2008, they may also be the key, along with nonviolent civil society, in ridding their region of ISIS and any other actual or potential threats.

Stephen Zunes is a professor of politics at the University of San Francisco, where he serves as program director for Middle Eastern Studies.

A version of this article originally appeared in The Progressive.

Impact to ICT
                

                      The mother and father of beheaded journalist James Wright Foley called on ISIS militants to spare the lives of other captured hostages as the authenticity of the barbaric video of his death was confirmed by the White House on Wednesday morning.

     White House National Security Council spokesperson Caitlin Hayden issued a statement to say that the 'US Intelligence Community has analyzed the recently released video showing US citizens James Foley and Steven Sotloff.'

     'We have reached the judgment that this video is authentic. We will continue to provide updates as they are available.'

     It was also announced that President Obama would interrupt his vacation at Martha's Vineyard in Massachusetts to make an announcement at approximately 12.45pm (ET).

     This comes hours after UK Prime Minister David Cameron cut short his vacation to return to head his governments response following the brutal murder of the American journalist by an ISIS jihadist thought to be British.

Diagram

	Cadit http://rt.com/files/news/28/bb/40/00/isis-2.jpg http://www.counterpunch.org/2014/09/04/the-rise-of-isis-and-the-ironies-of-us-foreign-policy/