Notes

Write a note in this area. IIn 1950 Alan Turing question first time was made question about artificial intelligence. Then aI turn brain circuits as a source of guidance. One path that was taken since the early attempts to perform intelligent computation by brain light circuits. Brain inspired model known as deep network or deep net architecture from successive layers of neurone like elements connected by adjustable beds called synapses after the biological counterparts.The key problem in deepnet is learning which is the adjustment of the synapses To produce the desired outputs to there input patterns.
Comparisons of deep network models with empirical physiological, functional magnetic resonance imaging, and behavioral data have shown some intriguing similarities between brains and the new models as well as dissimilarities.Reinforcement learning(RL) is brain like computation method.RL methods have been combined in recent AI algorithms with deep network methods applied in particular to game playing. Combining deep nets with RL produced stunning results in game playing. The AI systems and the neurone systems differences in structure are prominent. Cortical circuits in the brain are more complex than current deep network models and include rich lateral connectivity between neurons in the same layer.Some network models were developed initially to deal with perceptual problems.Ex:-image captioning ,vision and speech,judging humor,detecting sarcasm,online translation,flexible personal assistants,medical diagnosis,advanced robotics or automatic driving.
With these large research efforts, and the huge funds invested in future AI applications. Current AI modeling leans heavily toward the empiricist side, using relatively simple and uniform network structures, and relying primarily on extended learning, using large sets of training data. A large body of developmental studies have suggested that this fast, unsupervised learning is possible because the human cognitive system is equipped, through evolution, with basic innate structures that facilitate the acquisition of meaningful concepts and cognitive skills. Recent modeling of visual learning in infancy (13) has shown a useful combination of learning and innate mechanisms, where meaningful complex concepts are neither innate nor learned on their own. in general, the computational problem of “learning innate structures” is different from current learning procedures, and it is poorly understood. Combining the empirical and computational approaches to the problem is likely to benefit in the long run both neuroscience and AGI, and could eventually be a component of a theory of intelligent processing that will be applicable to both.finall thing is about this article that the Artifitial interlligent is in research situation for developing act as a human intelligence.But thre is a very difficult mechanism in human body related to biological,physiological and self learning mechanism.So it is very difficult to reach human like mechanism.But Can reach most like it. t's really easy to share with others. Click here ...