In a crude way division of work is breaking a goal into smaller tasks.

Division of work is concerned with breaking a big task into smaller ones. The resulting activities are therefore interconnected or linked.

Coordination is the process of facilitation these linked activities.

Linked Actions

On an assembly line a worker often picks up a part, does some work on it, and lays it down when finishes.

The next worker, seeing the part laid down knowns that it is now ready and the time has arrived for him to perform his operation.

One activity leads to another particular one through interaction. Perhaps it could flow through several supervisors or a production control system. The important point is that coordination occurs only when the proper actions are linked.

Elements in Coordination

Coordination has two essential elements; the work, tasks, jobs, or activities performed and their timing through a communication process.

Division of work, being concerned with the allocation of activities in order to achieve economies of effort, does not automatically provide for coordination.

The needs and facilitation of coordination is seen as being influenced by two principal items:

1. the degree and type of division of work
2. the environment of the organization.

To satisfy this need two principal types of coordination are used:

1. coordination by plan wherein long-term, fixed plans and schedules are used
2. coordination by feedback, where provisions are made for the flow of information about the work being coordinated.

Coordination is seen as the task of facilitation linked activities.

The process has two fundamental elements:

1. determination of adequate programs for these activities
2. communication to signal what program is to be used or the conditions for which a program is necessary and when action is needed.

Faced with a need for action, an individual might have a range of conditions to contend with in selecting a program; from those where programs are available, complete, and detailed to those where a program will have to be developed either through searching somewhere else for it, adapting an existing one, or creating a new one.

Communications are seen to have a wide range of forms from the specific, precise instruction or order, to the general information about the state of the organization and its environment.

The existence of these wide variations and the basic elements of coordination suggest the need for multiple means of achieving coordination from which the most acceptable element or a combination of them can be chosen.

The essential task in providing coordination is to find the best combination of these possibilities that can satisfy the coordinative needs of the organization.

Coordination is essentially an organizational problem. The extend and magnitude of the coordinative task is substantially influenced by other organizational decisions.

The task itself can be accomplished by a number of combinations of several different means.

The auto-associator learning paradigm, in which the goal is to store specific patterns for future retrieval.

Benefits of Distribution

Connection information distribution allows us to instruct parallel processing structures from outside the network, making their behavior contingent on instructions originating elsewhere in the network. This means, for example, that the way a network responds to a particular input can be made contingent on the state of some other network in the system, thereby greatly increasing the flexibility of parallel processing mechanisms.

Perhaps the most general way of stating the benefit of connection information distribution is to note that it is analogous, in a way, to the invention of the stored program. The use of centrally stored connection information to program local processing structures is analogous. This allows the very same processing structures to be programmed to perform a very wide range of different tasks.

A Distributed Model Of Memory

The auto-associator models are a class of related models that share the auto-associative architecture. That is, they all consist of a single set of units that are completely interconnected, auto-associators are limited by the fact thatthey can only train connections between units whose target activations can be specified from outside the network.

In spite of this limitation, auto-associators have several interesting properties. They can learn to do pattern completion and to restore distorted versions of learned patterns to their original form. They can learn to extract the prototype of a set of patterns from distorted exemplars presented during training.

In all versions of the auto-associator input patterns consist of vectors specifying positive and negative inputs to the units from outside the network, based on these external inputs and on the connections they receive from other units inside the network.

Patterns that are scaled by a network are called eigenvectors, eigenvector simply means "same vector." The magnitude of the eigenvector, as it is processed by the network, is called its eigenvalue.

The view that human memory is physiologically distributed within circumscribed regions of the brain seems to be quite a reasonable and plausible assumption.

But given the rather loose coupling between a psychological or cognitive theory of physiological implementation, we can ask, does the notion of distributed memory have anything to offer us in terms of an understanding of human cognition?

General Properties

Our model shares a number of basic assumptions about the nature of the processing and memory system with most other distributed models.

In particular, the processing system is assumed to consist of a highly interconnected network of units that take on activation values and communicate with other units by sending signals modulated by weights associated with the connections between the units. Sometimes we may think of the units as corresponding to particular representational primitives, but they need not. For example, even what we might consider to be a primitive feature of something, like having a particular color, might be a pattern of activation over a collection of units.

Connection information distribution

We argue that connection information distribution provides a way of overcoming some apparent limitations of parallel distributed processing mechanisms. Using connection information distribution, we can create local copies of relevant portions of the contents of a central knowledge store. These local copies then server as the basis for interactive processing among the conceptual entities they program local hardware units to represent.

With this mechanism, models can now be said to be able to create multiple instantiations of the same schema, bound appropriately to the correct local variables, subject to just the kinds of binding errors humans seem to make, we have not really done anything more than show how existing tools in the arsenal of parallel distributed processing mechanisms can be used to create local copies of networks.

Modular structure

We assume that the units are organized into modules. Each module receives inputs from other modules; the units within the module are richly interconnected with each other; and they send outputs to other modules. The state of each module represents a synthesis of the states of all the modules it receives inputs from.

Others will come from relatively more abstract modules, which themselves receive inputs from and send outputs to other modules placed at the abstract end of several different modalities. Thus, each module combines a number of different sources of information.

Units play specific roles within patterns

A pattern of activation only counts as the same as another if the same units are involved.

Relation to Basic Concepts in Memory

1. State as pattern of activation; In a distributed memory system, a mental state is a pattern of activation over the units in some subset of the modules. The patterns in the different modules capture different aspects of the content of the states in a kind of a partially overlapping fashion. Alternative mental states are simply alternative patterns of activations over the modules. Information processing is the process of evolution in time of mental states (?).

2. Memory traces as changes in the weights; Patterns of activation come and go, leaving traces behind when they have passed. What are the traces? They are changes in the strengths or weights of the connections between the units in the modules. Each memory trace is distributed over many different connections, and each connection participates in many different memory traces. The traces of different mental states are therefore superimposed in the same set of weights.

3. Retrieval as reinstatement of prior pattern of activation; Retrieval amounts to partial reinstatement of a mental state, using a cue which is a fragment of the original state. For any given module, we can see the cues as originating from outside of it. Some cues could arise ultimately from sensory input. Others would arise from the results of previous retrieval operations, feedback to the memory system under the control of a search or retrieval plan.

Use only the approprite actions of pursuit and avoidance and even these lightly.

When you are going about any action remind yourself what nature the action is if you are going to play picture to yourself the things which usually happen in the game some crash some push some use abusive language and others steal thus you will more safety go about this action if you say to yourself:

I will live for the swarm and keep my own mind in a state conformable to nature and in the same manner with regard to every other action for thus if any inconvenience arises you will have it ready to say it was not only to play what I desired but to keep my mind in a state conformable to nature and I will not keep it if I'm bothered at such things that happen.

We are disturbed by the principles and notions we form concerning things when therefore we are conflicted let us never attribute it to others but to ourselves that is to our own principles, an unistructed person will lay the fault for his own bad condition upon others, someone just starting instruction will lay the fault on himself, someone who is perfectly instructed wil place blame neither on others nor on himself.

The architect should be equipped with knowledge of many branches of study and varied kinds of learning, for it is by his judgement that all work done by the other arts is put to test.

Knowledge is the child of practice and theory. Practice is the continuous and regular exercise of employment where manual work is done with any necessary material according to the design of a drawing. Theory, on the other hand, is the ability to demonstrate and explain the productions of dexterity on the principles of proportion.

It follows, therefore, that architects who have aimed at acquiring manual skill without scholarship have never been able to reach a position of authority to correspond to their pains, while those who relied only upon theories and scholarship were obviously hunting the shadow, not the substance. But those who have a thorough knowledge of both, like men armed at all points, have the sooner attained their object and carried authority with them.

In all matters, but particularly in architecture, there are these two points:

• the thing signified,

• and that which gives it its significance.

That which is signified is the subject of which we may be speaking; and that which gives significance is a demonstrations on scientific principles.

The reasons for all this are as follows. An architect must have a knowledge of drawing so that he can readily make sketches to show the appearance of the work which he proposes. Geometry, also, is of much assistance in architecture and in particular it teaches us the use of the rule and compasses, by which especially we acquire readiness in making plans for buildings in their grounds, and righly apply the square, the level, and the plummet. By means of optics, again, the light in buildings can be drawn from fixed quarters of the sky.

It is true that by arithmetic that the total cost of buildings is calculated and measurements are computed, but difficult questions involving symmetry are solved by means of geometrical theories and methods.

What is an organization? A monkey, a building, a drone: each is a concrete object and can be easily identified. One difficulty attending the study of organizations is that an organization is not as readily visible or describable.

Exactly what is an organization? It is a building? A collection of machinery? A legal document containing a statement of incorporation? It is hardly likely to be any of these by itself. Rather, to describe an organization requires the consideration of a number of properties it possesses, thus gradually making clear, or at least clearer, that it is.

The purposes of the organization, whether it is formal or informal, are accomplished by a collection of members whose efforts or behavior are so directed that they become coordinated and integrated in order to attain sub-goals and objectives.

Perception and behavior

All of us at some point or another have had the experience of watching another person do something or behave in a certain way, saying to ourselves, "She acts as if she thought, ... " and then filling in some supposition about the way the other person looked at things.

Simple as the statement "She acts as if she thought ... " may be, it illustrates two important points.

First, what the person thinks she sees may not actually exist.

The second point is that people act on the basis of what they see.

In understanding behavior, we must recognize that facts people do not perceive as meaningful usually will not influence their behavior, whereas the things they believe to be real, even though factually incorrect or nonexistent, will influence it.

Organizations are intended to bring about integrated behavior. Similar, or at least compatible, perceptions on the part of organizational members are therefore a matter of prime consideration.

If a system is to be stable the number of states of its control mechanism must be greater than or equal to the number of states in the system being controlled.

In trying to understand what is happening around us we are faced with a fundamental problem. In approaching any situation, the system trying to understand it, does not attempt to gather all information. Instead it selects certain facts and searchers for others.

This selection of some items and ignoring of others is a process of abstraction.

It is the abstracting form a real or if you will empirical situation the things seemingly most important to deal with.

In this process of abstraction and model building we deliberately select a few items, ignore may others, and then place the items chosen in a particular relationship to one another.

In doing so we are intentionally ignoring facts or relationships that can influence the type of situation under study.

The problem it to select the most meaningful elements and relationships and dropout the rest.

Those who use abstraction skillfully know well that they neither have all the facts nor have considered all the relationships bearing on the outcome of what they are analysing.

We do not use the abstractions from one situation in another setting without carefully examining the fit. Neither do we expect a model to handle all aspects of a situation.

We shall be dealing with many abstractions and models, not with the intention of exactly mirroring the real world but with the objective of clarifying our perception of its most essential features.

Abstractions and models are mechanisms for economizing both time and effort, but like any tool they must be used within their limits.

Model your goals

Taking the abstracted elements, a character with the flat tire begins to connect them into a pattern.

Better yet, he weaves them into a model of the confronting situation, which we can use both to understand his plight and figure out what to do about it.

The parts of this model would probably include, among other things, the flat tire, the image of the spare in the trunk, the telephone, the service station, a forthcoming business meting, etc.

A second model would contain the telephone, the service station, and the repairman there.

Finally, he concludes that he will call a cab and leave his wife to deal with the flat tire as best as she can.

These are extraordinarily elementary models, but they serve a very practical purpose.

With them the main character in our illustration can see the likely consequences of various courses of action.

We can find out these things by doing them directly by actually handling the tire and observing that we get dirty, or by calling the repairmen and waiting for him and learning that it takes too long.

In the age of big data; information models are good.

• For any given size of data, the bigger the model, the better it generalizes, provided you regularize well.
• This is obviously true if your model is an ensemble of smaller models.
• Adding extra models to the ensemble always helps.
• It is a good idea to try to make the data look small by using a big model.

By using the model, however, we can make some reasonable predictions about what will occur and thereby accept or reject the choices open to us.

Several references have been made with the intent of this guide to provide conceptual tools for analysis. As with any other tool models, abstractions and generalizations are useful only when within their limitations.

Organization refers to the tendency of all species to systematize or organize their processes into coherent systems which may be either physical or psychological. Adaptation is the balance between the independent processes of assimilation and accomodation.

Jean Piaget's theory of cognitive development proposes that humans cannot be given information, in which they immediately understand and use. Instead, learners must construct their own knowledge. They build their knowledge through experience. Experiences enable them to create mental models of the world. These models are changed, enlarged, and made more sophisticated through two complimentary processes: assimilation and accommodation.

Definition of intelligence

Piaget's definition of intelligence itself does not consist of an isolated cognitive process. It is not, one form of structure among others; it is the form of equilibrium towards which all the structures or cognitive processes tend.

Intelligence is only a generic term to indicate the equilibrium of cognitive processes.

He believed, human beings inherit a tendency to organize their intellectual processes and to develop particular adaptations to their environment.

Intellectual adaptation is also an exchange between a person and its environment and involves the same two processes of assimilation and accommodation found in biology.

Assimilation involves the person dealing with the environment in terms of its structures, while accommodation involves the transformation of its structures in response to the environment.

The particular ways in which an organism adapts and organize its processes depend also on its environment and learning history.

Cognitive constructivism

Cognitive constructivism is based on two different senses of construction. First, on the idea that people learn by actively constructing new knowledge, not by having information poured into their heads. Moreover, constructivism asserts that people learn with particular effectiveness when they are engaged in constructing personally meaningful artifacts (e.g. computer programs, animations).

View of learning

Because knowledge is actively constructed, learning is presented as a process of active discovery. The role of the instructor is not to drill knowledge into students through consistent repetition, or to goad them into learning through carefully employed rewards and punishments. Rather, the role of the teacher is to facilitate discovery by providing the necessary resources and by guiding learners as they attempt to assimilate new knowledge to old and to modify the old to accommodate the new.

Thanks to Sonko for the oportunity to talk in detail about this new Brood War AI competition on The Undermind podcast explaining the current problem with StarCraft: Brood War AI competitions and this Linux new alternative.

{% youtube qYGAteZrBl8 %}

It was great to hear again from Johan de Jong the author of BananaBrain one of the top competitive protoss bots, he talked about his work around Dark Templar and Reaver/Shuttle micro as well as goin into details about his development process and path-finding fixed issues, BananaBrain was 5th in CoG 2019, Johan comment about learning strategies used in competitions raising the question about the amount of rounds available since this affects directly the learning capabilities and performance.

Bryan Weber the author of CUNYBot is a resercher at the College of Staten Island, he is interested in macroeconomics and works with a couple of students that every few semesters make modifications, and improvements on the bot. It was interesting to hear about his experience and adventures enabling the Python interpreter inside CUNYbot and through the land mine of building the bot for competition and also enable a modern machine learning stack as well as his comments on genetic algorithms.

Check out The Undermind podcast and Sonko's Making Computer Do Things where he is writting a book about the insides of StarCraft: Brood War AI and BWAPI bot development.

{% youtube yuUxqvslhBY %}

We talk about Python and a variety of different topics. Happy listening!

Check out The Undermind podcast and Making Computer Do Things