NAME: OBENG TOKU JEFFREY
INDEX: 02200918
COURSE: ARTIFICIAL INTELLIGENCE
1. An agent is anything that can be viewed as perceiving its environment through sensors and
acting upon that environment through actuators but an intelligent agent is a software agent
that has some intelligence like autonomous programs used for operator assistance or data
mining sometimes referred to as bots and they act independently to achieve certain goals and
gives feedbacks.
2. Supervised learning is the technique of accomplishing a task by providing training,
input and output patterns to the systems whereas unsupervised learning is
a self-learning technique in which system has to discover the features of the input population
by its own and no prior set of categories are used.
3. -Accessible/inaccessible- This refers to the possibility for an agent to obtain complete and
accurate information about the environment state .
-Determinism/non-determinism- In a derterministic environment, any action has a single
guaranteed effect and no failure or uncertainty. On the other hand, in a non-deterministic
environment , the same task performed twice may produce different results or may even fail
completely.
- Episodic/non-episodic- In an episodic environment, each agent’s performance is the result of a
series of independent tasks performed. There is no link between the agent’s performance and
other different scenarios. In other words, the agent decides which action is best to take, it will
only consider the task at hand and doesn’t have to consider the effect it may have on future
tasks.
- Static/Dynamic- An environment is static if only the actions of an agent modify it. It is dynamic
on the other hand if other processes are operating on it.
- Discrete/Continuous- An environment is said to be discrete if there are a finite number of
actions that can be performed within it.
4. In biological Neuron, the task of receiving the incoming information is done by dendrites, and
processing generally takes place in the cell body. Incoming signals can be either excitatory —
which means they tend to make the neuron fire (generate an electrical impulse) — or inhibitory
— which means that they tend to keep the neuron from firing.
Most neurons receive many input signals throughout their dendritic trees. A single neuron may
have more than one set of dendrites and may receive many thousands of input signals.
Whether or not a neuron is excited into firing an impulse depends on the sum of all of the
excitatory and inhibitory signals it receives. The processing of this information happens in soma
which is neuron cell body. If the neuron does end up firing, the nerve impulse, or action
potential, is conducted down the axon.
Towards its end, the axon splits up into many branches and develops bulbous swellings known
as axon terminals (or nerve terminals). These axon terminals make connections on target cells.
Artificial neuron also known as perceptron is the basic unit of the neural network. In simple
terms, it is a mathematical function based on a model of biological neurons. It can also be seen
as a simple logic gate with binary outputs. They are sometimes also called perceptrons.
Each artificial neuron has the following main functions:
Takes inputs from the input layer
Weighs them separately and sums them up
Pass this sum through a nonlinear function to produce output.
5. An artificial neural network is the piece of a computing system designed to simulate the way
the human brain analyzes and processes information. Artificial neural network have self-
learning capabilities that enable them to produce better results as more data becomes
available.
6. A neural network does not store any knowledge, at least not in the form of pictures, sounds
and facts that you can extract - like you would if you extracted information from a memory
device.
Instead, a neural network is like a filter that can reliably identify a certain digital representation
of an object.
The settings for a given filter simply look like a list of numbers . The training process involves
finding the best set of numbers for a given pattern recognition task.
Knowledge in artificial neural network is contained as a model thus network of operators and
coefficient of operators
Knowledege is contained in the weights and biases of the model that learns to map inputs to
the correct outputs through a process of error reduction. Once error is minimized, the
knowledge is embodied by the weights and biases (which multiply and are added to the input,
respectively), that lead to the best results.
The neural network model store the weights that make the function of function of function
takes the choice of the right answer. For example classification problem on cat or dog image . In
training process the gradient descent work to get less expected error then take this weights as
the features then by the max probability the model will choose the type : cat or dog.
7.
8. AI can help in improving product circulation and asset utilization through smart inventory
management, pricing prediction, and predictive maintenance in Ghana. AI can help improve
processes, building, and correcting the reverse logistics infrastructure.
Also for industries in Ghana, AI can boost growth and profitability and help in transforming
businesses.
It can also it can improve personalization of products and services through automating routing
tasks through robots and autonomous vehicles which will improve productivity gains in Ghana.
AI can benefit Ghana by eliminating waste and plundering of resources through better designs
of materials, products and services.
9. During this covid 19 era, AI can be the solution to students development through learning. AI
can be used as a tool in arears where teachers are limited so looking at this circumstance, AI
can play a major role since physical learning will not take place because of the covid.
Also as we can see, machine learning applications process information more quickly and in
larger quantities than humans do. Teachers notwithstanding have other responsibilities outside
the classroom and can’t even find time in these difficult times hence the use of AI is the best
choice.
An AI with a rich data can also provide a more personalized learning experience, an experience
that is equitable and enjoyable for all, thus helping learners to even forget the difficult times
ahead with interesting stuffs like providing feedbacks and supports whiles learning at the same
time.
10. The main reason why we use sigmoid function in an artificial neuron is because it exists
between (0 to 1). Therefore, it is especially used for models where we have to predict the
probability as an output. Since probability of anything exists only between the range of 0 and 1,
sigmoid is the right choice. The function is differentiable.
