“The human brain, then, is the most complicated organization of matter that we know.”
Isaac Asimov

If someone asks what you recall when you look at the following pictures, I can hear you say ‘President Obama’ and ‘Statue of Liberty’. You just see a fragment of the pictures and remember them.

So, how does it happen? This is just a simple task for the brain. It stores an image and retrieves it whenever a part of it is seen. Amazing features of the brain, especially its power to learn and make decisions, inspires computer scientists in the field of artificial intelligence.

In computer science, an artificial neuron is a simple computational model of a neuron in the brain that excludes biological properties. Artificial neural networks (ANNs) are composed of artificial neurons, and they are utilized to solve specific problems, especially those that require learning and decision-making. ANNs may not be the best solutions in various machine learning problems; however, they are accepted as strong alternatives. Although ANNs don’t claim to be so, currently they are not even close to producing a simple model of the brain. Let’s take a short journey into the world of ANNs to experience the extreme difficulty of modeling the brain.

Some Applications of ANNs

Figure 1: Overview of ALVINN structure. Images obtained from the camera installed on the vehicle are provided to the ANN, and ANN decides the steering angle.

(adapted from: http://virtuallab.kar.fei.stuba.sk/robowiki/images/e/e8/Lecture_ALVINN.pdf).

ANNs have various applications in very large spectrum of problems that require learning, such as the Autonomous Land Vehicle in a Neural Network (ALVINN). The structure of ALVINN is shown in Figure 1. The ALVINN project by Carnegie Mellon University started in 1986 and aims to make a vehicle without a driver (Mitchell, 1997). In this project, ANN learns the steering habits of a driver. A camera is mounted on the vehicle to capture the images of the road. With respect to the continuous images provided, ALVINN determines the steering level with 45 different angle positions from sharp left to sharp right. Steering is updated 15 times per second so that it allows real-time control while driving at 55 mph. The system is trained by the data obtained from a human driver in a simulator and a real vehicle. ALVINN was able to speed up to 70 mph and successfully drive at 55 mph for 90 miles.

Figure 2: Handwritten zip codes (LeCun, et al., 1989)

Another example is handwritten zip code recognition (LeCun, et al., 1989). Zip codes from US Mail written by various people with large variety of styles and sizes were used in the experiments. Figure 2 presents some examples of zip codes in the experiment database. After the ANN was trained with more than 7,000 digits in the zip codes, it was 99% successful in recognizing around 2,000 digits in new zip codes.

Learning and Decision-making in ANNs

In order to understand the challenges better, we will first examine learning and decision-making in neurons and ANNs on simple examples.

Figure 3: (a) A typical neuron (adopted from http://commons.wikimedia.org/wiki/File:Neuron_-_annotated.svg), (b) artificial neuron in computer

Figure 3(a) illustrates a typical neuron which is the constituent of brain’s complicated network structure. Each neuron receives information as signals via dendrites, then evaluates it and generates a signal that is transmitted through its axon. A neuron has many connections between its dendrites and the axons of various other neurons. Figure (b) demonstrates an artificial neuron in computer science. It is considered a function: dendrites as the inputs of the function and generated signal via the axon as the output of the function.

Let’s see an example of an artificial neuron that understands if a given produce is a red apple or not. Think about how you understand whether a produce is a red apple or not. You see the shape and the color. However, it might be an artificial one for decoration. Then you can taste it and you get the sweetness of the apple. Similarly, our neuron receives three pieces of information as the input; ‘has circular shape?’, ‘is sweet?’, and ‘has red color?’. If the output is ‘yes’, that means the neuron recognizes the produce as a red apple. Otherwise, it will be ‘no’, which means the produce is not a red apple (Figure 4). Here, the neuron’s function is defined in such a way that it only generates ‘yes’ when all the inputs are ‘yes’.

Figure 4: Example inputs and outputs for the artificial neuron.

In an artificial neuron, some of the information can be more important than the others. For instance, to have red color may be more valuable in determining the price of produce. Assume that round shape and sweetness has equal value of $1; however, having red color is $2 – twice as valuable as the other features (Figure 5).

Figure 5: Artificial neuron with different input weights. Arrow thickness indicates the importance.

So, what is the big fuss about artificial neurons if they are only functions? In fact, the main feature of artificial neurons is learning. Considering the last example above, the neuron initially does not know the importance of the dendrites, i.e. the weights of inputs are all the same. If not trained, the neuron will generate the following answers which are sometimes wrong as indicated in Table 1.

Table 1: Artificial neuron before training; highlighted answers are wrong.

In real life, a teacher trains students. For instance, the teacher asks a question and if the received answer is not correct, she provides the right answer. Students learn the right answer and use this correct information in their lives. It is similar in artificial neurons as depicted in Figure 6. When the response of the neuron is incorrect, it adjusts the importance of the dendrites with respect to the correct answer hence it answers the same question correctly next time. During the training session, the neurons will be continuously asked the values of all the produce until it learns them all.

Figure 6: The learning process of the artificial neuron.

What if the problem gets complicated? Then one artificial neuron will not be sufficient, and we will need a network of neurons; ANNs. A more complex problem, ‘learning the digits’ is indicated in Figure 7.

Figure 7: (a) Digit learning problem, (b) ANN structure that learns digits. Due to the difficulty, only the connections between the input layer and first / last neurons in the middle layer are shown.

ANN has 3 x 5 = 15 input units like receptors of an eye retina. Each input unit corresponds to one square in the digits; either filled or blank. Each input unit is connected to the dendrites of all neurons in the middle layer. The output of each cell in the middle is connected to the dendrites of all neurons in the output layer. There are 10 output neurons corresponding to the digits from 0 to 9. After the ANN is trained, it provides a correct answer to the given digit as input. When digit ‘3’ is provided to the network, the neuron labeled with number ‘3’ in Figure 7(b) is triggered and outputs ‘yes’ whereas the rest of the neurons output ‘no’.

Figure 8: Faulty digit ‘3’ with a missing black square on the top right side.

Initially, all neurons in the network have equally weighted dendrites. After a reasonable amount of training, neurons adjust their weights, and ANN is able to identify digits. Here, we have some major challenges: what does ‘reasonable amount of training’ mean? When the ANN is undertrained, it will not always answer correctly to the digits given in Figure (a). In the other case, when the ANN is overtrained, it will memorize the digits provided during the training and will not recognize the faulty ones such as the one in Figure 8.

Challenges of ANNs

Beyond the mentioned the overtraining / undertraining problems, ANNs have a bigger challenge – how to determine the structure of ANN that fits the problem? In the digit learning example, we’re lucky because the structure is provided in Figure 7(b). However, the outcome of the solution may drastically depend on the number of neurons and the connections among them which is indeed a hard problem for ANNs.

The huge capability of the brain in learning and decision making comes from the huge number of neurons – around 100 billion – and the enormous amount of connections among them – from 100 to 500 trillion. The challenge to design such a huge network requires huge computation power. With the increasing number of neurons, ANN dramatically slows down especially during the learning process. Here, our example is a simple learning task of 3×5 pixel digits compared to the brain’s acquisition capacity of hundreds of images in our daily life. 

When the number of neurons gets larger, the reliability of network also reduces. Small adjustments in weights may change the entire behavior of the network hence it is easy to lose control of ANN. In contrast, the brain has a robust system, and its fault tolerance is admirable. Although neurons die every day, this doesn’t affect its performance significantly. The training method and how to update the weights are other hard problems leading to many different approaches in the neural computation field.

We have presented some simple tasks that can be solved using a few neurons and their challenges. On the other hand, consider the thousands of problems, various and incredible amount of information we have learned, and the thousands of decisions we make. The brain is truly amazing from the computer science perspective.

Bibliography

• Hertz, J. A., Krogh, A. S., & Palmer, R. G. (1991). Introduction To The Theory Of Neural Computation. Reading, MA: Addison-Wesley.
• Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational properties. Proceedings of the National Academy of Sciences of the USA , 79, 2554-2588.
• LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., et al. (1989). Backpropagation applied to handwritten zip code recognition. 1 (4), 541-551.
• Mitchell, T. M. (1997). Machine Learning. McGraw-Hill.

Increasing brainpower

We can improve our brain’s memory, creativity, and intelligence by our own conscious effort and free will. Even though our brain is made of nerve tissues, it can grow if it is used, just like a muscle. Scientists are constantly amazed at its plasticity “ the ability to grow. Even for people over 80 years old, significant life-quality improvements can be achieved through intellectual activity.

Researchers at the University of California-Los Angeles studied the brains of 20 dead people. After examining the dendrites (tree-like communicating arms between muscles), they discovered that their length increased proportionally with a person’s education and lifestyle. Those with a college education and a mentally active lifestyle had longer dendrites than those with less education and an intellectually inactive lifestyle.

Animal studies seem to confirm the same result. For example, rats exposed to maze learning show an increase in dendrite growth and enhanced problem-solving ability. They form new synapses between neurons, which facilitates further learning. When they are moved to dull, non-challenging environments, dendritic material decreases and synapses regress. Neurons can grow and change throughout one’s life.

French philosopher and mathematician Rene Descartes (1596-1650) once said: It is not enough to have a good mind. The main thing is to use it well.(1) In this ever-changing information society, successful adaptation depends on expanding our minds through learning and creativity. Knowledge helps us advance to happiness, because happiness usually is tied to less stress (in our career or daily life), gives us greater travel and leisure opportunities, more autonomy and even more money. Love grows in a relaxed and happy atmosphere, so even emotional well-being depends on improving our brainpower.

By stimulating our brain more intensively, a curious thing happens: The inter-connections between neurons increase by developing new dendrites. These surplus connections make our brain work better, improve our memory, and protect us against diseases like Alzheimer’s by providing alternative connections.

Learning and brainpower

An increased sense of self-confidence and awareness originates from a large fund of knowledge. Even the number and variety of friends we have is directly proportional to the number of topics of interest and discussion we acquire. Knowledge also improves our ability to foresee future political, economic, and historical trends. Moreover, an improved understanding of history and cultures help us avoid the hazard of prejudice.

Understanding the world is like a jigsaw puzzle. The more pieces that we can fit in, the clearer the image and the greater the urge to learn and fill in more pieces. The more we learn, the more we wish to continue learning. Increasing knowledge is like an avalanche; for it gains a momentum of its own once it starts. Perseverance and some initial prompting are required, but the rewards soon pay off. Minds are kept young by continual use, and mentally active people tend to live longer. Learning is as important to our brain as exercise is to our body. Hence the process of learning should not cease right after graduating from high school or college.

Students are presented with an enormous amount of information to learn and memorize during the academic year. During vacation time, however, they shy away from reading or learning even about non-curricular topics because of the mistaken notion that the brain has a limited capacity and that new information will overwrite previous information. The brain has a virtually unlimited capacity to absorb, sort, and retain information. But stimulation is required. An athlete improves by exercise and training; the brain gets into shape the more it is used.

According to Life magazine’s July 1994 feature article on Brain Calisthenics, Golden claims that exercising your brain may do as much for your health as exercising your body. Research on an elderly group of nuns in Minnesota revealed that a daily diet of brain games kept them healthy, youthful, and relatively free from Alzheimer’s and other degenerative brain disorders. And, they were happy, active, and mentally sharp well into their nineties. Researchers attribute this to the brain’s capacity to grow new connections after receiving the proper kind of stimulation. Although the connection between continued brain activity and health remains unclear, we can say that neural stimulation seems to have a direct role in keeping the brain and body balanced, energetic, and healthy. And, it is surmised that increased brain stimulation provides more pronounced and long-lasting benefits.

We can increase our dendrites by engaging in newer activities. When we learn something, we use our whole brain and build new brain circuits. But once something becomes a routine, we only use a small portion of our brain, leaving the rest to atrophy. To prevent the loss or actually to increase the number of dendrites, they must be stimulated. In a Life magazine interview published in July 1994, Arnold Scheible, head of UCLA’s Brain Research Institute, suggested: The important thing is to be actively involved in areas that are unfamiliar to you. Anything that’s intellectually challenging can probably serve as a kind of stimulus for dendritic growth, which means it adds to the computational reserves in your brain.

However, the article pointed out a caveat for the occasional brain developer. It seems that although learning a new skill creates more neural dendritic connections, the growth stops once the skill is learned and the new connections may actually atrophy. Thus, the brain needs random and interactive exercise so that it cannot learn the exercise so well that it becomes a routine and so that it can better learn new things continually.

Learning is an art that requires practical tools to gather a broad knowledge base. For example, Dr. S. Ray has an interesting suggestion: Look up unfamiliar words in the dictionary and then write a reminder by the word indicating where you encountered it, whet-her in a book, a newspaper, or a conversation. If you saw it in Newsweek, write NW beside the word. If your professor mentioned it, write his name next to the word. If you come across a word in this article, put a smiling face near it. Next time you encounter this word, your previous annotation will help you form a better association and you will remember the word better.

Once you start learning new words, it is a pleasant surprise to encounter them again. Each new word becomes a personal friend that reinforces a memory. Consider the dictionary one of your most interesting friends. The more words we learn, the more we become aware of our surroundings. Words enrich our memory. Words form the thread on which we string our experiences, said the British philosopher Aldous Huxley (1894-1963).

Physical activity and brainpower

Physical activity increases mental function. Exercise induces the growth of capillaries (tiny blood vessels) in the brain. Aging can lead to the brain receiving less blood. Exercise throughout life works against the decreased mental functioning associated with old age. Yet, one must not overemphasize physical exercise.

In their book Healthy Pleasures, Ornstein (a psychologist) and Sobel (a physician) argue that our current health practices should be shifted toward a more intellectual approach. They claim that diets and physical exercises can punish and even harm the body, and that they might have side-effects and only a limited effectiveness. They opine that some of the rigorous body controls we tend to practice are more linked to the Protestant work ethic than real health benefits. Hence going to the gym is a work-out.

Stress and brainpower

One side-effect of stress is dullness in the brain. Therefore, whatever removes stress increases brainpower. There are several relatively new methods to improve brainpower (intelligence, creativity, learning ability). For example, listening to a precise combination of audio signals embedded on a cassette or CD beneath soothing music and environmental sounds can give the brain a very specific audio stimulus that gently creates deep meditation, removes stress, and creates emotional healing at a deep level. This causes new connections to be created in the brain.

This is accompanied by a deep, trance-like meditative state in which the brain produces a whole host of pleasurable neurochemicals, such as endorphins. Such a trance or meditation can be attained easily during deep and concentrated prayer. A soothing and relaxing atmosphere can be achieved during chanting, remembrance, or reciting holy texts and hymns.

The new pathways caused by these meditative states connect and synchronize the brain’s hemispheres, thereby causing whole brain functioning. The improvements in brainpower include learning, intuition, mental clarity, creativity, focus and concentration, and intelligence. This research is backed by Centerpointe Institute, which has a commercial product (Holosync) based on the above principle.

Stress also is tied to the burdens we are obliged to carry. Usually we think that we control our lives entirely and thus can control everything around us. As this is not even near the truth, the resulting condition is stress accompanied by depression. Again, a fine balance between faith in destiny and free will help us remove this stress and live an alleviated and spiritually relieved life. Said Nursi analyzes this concept in his Twenty-sixth Word.(2)

In addition to removing stress, the nervous system’s reorganization of itself to a new and higher level increases the stress threshold. At that point, many uncomfortable, dysfunctional feelings and behaviors go away, even if they might have been persistent until then. This is a deep and dramatic change in mental health: the release of anger, fear, and sadness, as well as the release of self-defeating behaviors, childhood traumas, and limiting decisions. Once these are gone, we can expect better relationships to emerge.

Thus it is like a virtuous cycle, because people who reach higher levels want to move to deeper meditation levels, just as athletes increase their mileage after mastering a certain distance. In these in-creased levels, the mind expands, grows, and becomes self-aware to a greater extent. Perhaps it also experiences a deeper meditative experience.

Health and brainpower

Adding years to your life and life to your years have always been challenging. The first one has been achieved for some, as life expectancy in developed countries increased by 30 years during the twentieth century due to improved food supply, housing, medicine, and many other factors. However, research in the last few decades proves that one can become even smarter by dendrite generation. At first, researchers told us that life-long physical training was one way to keep in good health. Now, since scientists know that the brain can be developed and enlarged, brain calisthenics have become even more important. The age-old dilemma of mind over matter has been resolved in favor of the mind.

A group of researchers has demonstrated that pleasure and positive states of mind are better for our health. This new intellectual approach to health is not only more powerful, but also has no side effects. Central to this claim are recent findings that even getting an education may add as much as 10 years to your health. That is why National Geographic featured John de Rosen in its 1986 book The Incredible Machine, which discussed old age. De Rosen, an artist, continued to paint until the week he died at age 91. The book notes: Some scientists believe that retirement to a sedentary lifestyle initiates or aggravates medical problems, thus shortening life. According to a study of retired people, adults over 65 can learn a creative skill, like oil painting, as readily as younger students. So retiring from a job in a sense means retiring from life unless supplemented by some other (preferably new) activity.

Investigating mental processes and brain efficiency

With their new imaging machines, scientists literally look into the brain and photograph the paths of mental processing to learn how the brain handles information. Each of the 100 billion neurons has dendrites (receptors), a central processor, and a cable to send the messages to the next neuron. Some years ago, scientists thought that these physical aspects were fixed at birth. Then Marion Diamond, a pioneer brain researcher who dissected Einstein’s brain, published Enriching Heredity. In it, she claimed to have found that the key areas of Einstein’s brain were very rich in dendrites due to the increased usage, and thus established that the brain is not fixed by heredity.

Another aspect of brainpower is efficiency. Dr. Richard Haier, a professor of psychology at the University of California, Irvine School of Medicine, used PET (positron emission tomography) scan images of brain metabolism to indicate mental efficiency. Newsweek (29 February 1988) reported his finding that smarter brains use less energy. Wired (May 1994) introduced to the general public his first works using PET to analyze the brain changes of Tetris players. In this article, he revealed the importance of neural efficiency. In other words, give a smart brain a hard cognitive task, like Tetris, and it will quickly learn to solve it using less of the brain and less rigorously. Less efficient brains seem to have difficulty localizing the task to the most appropriate processing centers. Therefore, there is wasted brain energy and needless redundancy (noise) in neural-net processing activity.

Newsweek (27 March 1988) featured Haier’s PET scans of SAT (Scholastic Aptitude Test) takers. The outcome seemed to differentiate be-tween sexes. Smart men who scored above 700 on the SAT math section worked their brains harder (less efficiently) than smart women. The PET images reveal how efficiently the brain works when processing a cognitive task. Therefore, before and after PET images may show how smart the brain, or neural-cognitive system, is as a function of how fast it learned how to minimize extraneous brain processing areas and focus energy on smaller, more productive areas.

We have been led to believe that we use very little of our brain. Ironically, the smarter the person is, the less of his or her brain seems to be involved in any particular task. It seems that dendrites use the shortest or most feasible path possible, and that the more numerous and longer the dendrites are, the more likely they are to have shorter paths between the nodes in the brain’s neural network. When the mind starts to process a task, it apparently engages a greater area of the brain to feel it out. However, the smarter brain-mind system will narrow in on the brain’s most appropriate processing area(s). Then, the rest of the brain is released to do something else, such as noisy chatter or just rest (which is rare). A less intelligent system might use more of the brain than is necessary. This may create a source of noise on the neural-net that distracts, disrupts, or derails the fast and efficient (consistent and accurate) data processing by the appropriate brain center(s).

Brain efficiency seems to be highly correlated with intelligence (or brainpower). Apparently, the less moving parts the less friction and noise! This would agree with certain research findings of meditators whose quieter and more alpha- and theta-dominant brains appear to be better at various cognitive and mental reflex tasks.

Conclusion

In conclusion, brainpower depends on many things: daily diet, physical and mental exercise, emotional state, stress, heredity and so on. It is not fixed or static, but has the ability to change and progress, so one can improve it by a combination of techniques that suit the individual. The discovery of new or improving existing techniques is open for further research in cognitive science.

Footnotes

1. http://serendip.brynmawr.edu/Mind/Descartes.html#Descartes.
2. The Words is available online at:www.sozler.com.tr/risnur/warning_word.htm.

References

• Centerpointe Institute, Holosync, http://www.trans4mind.com/holosync/.
• Diamond, Marion. Enriching Heredity: The Impact of the Environment on the Anatomy of the Brain. Free Press: 1988.
• Ornstein, R. and D. Sobel. Healthy Pleasures. Addison-Wesley, 1989.
• Poole, R. M. (ed.) The Incredible Machine. National Geographic Society: 1992.
• Report from the Biomedical Newsletter. Lippincott-Raven Publishers, n.d.
• Sahelian, Ray. Be Happier Starting Now: A Medical Doctor Explores the Fascinating Field of Happiness. Longevity Research Center: 1995. See Chapter 9.
• www.brain.com.