Hi,

Brief introduction: I have almost 5 years experience working in eCommerce and I am transitioning to the field of AI. I have seen AI & machine learning being used in my field and I believe there is still more to come in the future.

Given that AI is a very important technology and a key components of the 4th industrial revolution, I think its important to share my knowledge to spur someone to take an interest in this field. This tutorial will start from the scratch and will also contain links to important readings. Please do read these links. I will make sure my explanation is as easy as possible so that a 5 year old can assimilate the concepts.

Requirements: Come with your drive & passion, dedication, a laptop and a notebook.

As we advance on this topic, we would do some coding and maths - don't worry its easy if you are committed to it.

The first few weeks would be an introduction to understand the terms and concepts. Trust me, machine learning as a lot of terms that are sweet to know.

Finally, I will be posting twice a week or more when I have the time. Feel free to ask questions on the thread and I'll answer you.

Thanks.

Let me book space here...

Do{
FollowThread();
}While( threadContent == knowledgeable )

am in

Lesson 1: AI came from one simple question: Can computers learn to think like humans?

Humans can easily identify objects because the brain has “seen” (learned) the images of those objects before – as input, processes it and then identifies the object as a dog, book, stick e.t.c. However, this is extremely difficult for computers. Why? Because computers are primarily programmed for computational results. Computers compute!

A computer can multiply 123736 by 352635 and give the results in nanoseconds but finds it hard to identify a puppy in a picture. To solve this problem, what if we try to replicate how the human brain works in a computer? Just what if…

Enters Neural Network

Now, think about a simple network that takes many input, processes them and gives an output then you have a neural network.

How it works:

Neural networks take in a large number of input, known as training examples, then uses the examples to create rules for recognizing patterns. This means, many pixels of a dog’s image can be ‘fed’ into the computer today to train it, so that when next you ask it to recognize dogs in various pictures, it would give the correct answer. By increasing the number of training examples of different dog pics you show to the computer, it can learn more and so improve its results – it’d even identify a dog in superman’s costume.

Why neural networks in computers?

As explained earlier, simply to replicate how the brain works in computers and enable computers to recognize patterns/objects.

It resembles the brain in two aspects:
a) input is acquired by the network through a learning process. (The learning process is the process whereby the image is shown to the computer so that it learns to identify objects in the image in the future)
b) interconnection strengths between the network are used in results (will explain this later)

I’d continue with the developments on neural networks.

Let me know if you have questions.

just the kinda thread I've been looking for. following...

Go ahead sir

Which programming language must one know for AI?

billpete89:
Which programming language must one know for AI?

Tensor flow, pythorch IBM watson

billpete89:
Which programming language must one know for AI?

Depends on what you want to use it for. I recommend learning Python for starters. Its easy and versatile. As you advance, you will learn a few more libraries in python that helps you build your own solutions.

Thanks.

following closely

As an engineer, the mention of the word "machine" bring things like internal combustion engine, pump, motor, compressor, transformers, etc to mind.

1) Is the Machine in the term "Machine Learning" referring to these items above or computer system ?

2) Still on terminology, what is Deep Learning (DL) and how do these terms AI, ML, DL and Neural Network (or Artificial Neural Network_ANN) relate to each other

Thank you

Efiko:
As an engineer, the mention of the word "machine" bring things like internal combustion engine, pump, motor, compressor, transformers, etc to mind.

1) Is the Machine in the term "Machine Learning" referring to these items above or computer system ?

2) Still on terminology, what is Deep Learning (DL) and how do these terms AI, ML, DL and Neural Network (or Artificial Neural Network_ANN) relate to each other

Thank you

Good questions:

1) Is the Machine in the term "Machine Learning" referring to these items above or computer system ?

It generally refers to a computer. However, you can have computerized machine like robots, dispensers, filters and so on. These are also machines than can be computerized to learn how to do want humans do. So yes, the machine in machine learning cuts across all fields once the 'machines' can be computerized to learn how to improve its performance as it does more of the task - without being explicitly being programmed to improve its outcome.

Lets say a self-driving car has been programmed to drive you within Lagos. Now if you wanna get to Ibadan and it gets to drive to you unknown places (places it has not seen or programmed with) because it can learn like a human being to navigate unknown territories - noting and storing the landmarks, potholes, traffic stops and so on. Its a machine that is learning. You don't have to be updating or coding new location everytime it needs to go an unknown place. It has learned by itself to do that. And if it improves next time and gets to Ibadan faster or smoother than the first time, then its learned to improve its performance. This is a classic example of machine learning. Its applications are limitless.

2) Still on terminology, what is Deep Learning (DL) and how do these terms AI, ML, DL and Neural Network (or Artificial Neural Network_ANN) relate to each other


To give a perspective, AI is the god, machine learning is its main oracle while deep learning is one of the prophets that talks to the oracle.
Artifical Intelligence is human intelligence in machines. Machine learning is when the machine learns - feeding the machine with things I would learn with - primarily data. Deep learning is an approach to machine learning just like machine learning is to AI.

Machine learning aims to bring artificial intelligence through learning from the data. Thus ML can be considered as one of the approaches towards Artificial Intelligence. Deep learning was inspired by the structure and function of the brain, namely the interconnecting of many neurons. Artificial Neural Networks (ANNs) as I explained above are networks that mimic the biological structure of the brain so that they cam be used in deep learning and machine learning.

Its like this.

AI --> ML --> DL --> NN
god --> Oracle --> Prophet --> worshipers

PS: Remember you need to be a worshiper to access the gods. And that's why we are starting from there.

Reference for more understanding:
here

Thanks for the prompt response and the additional reference source provided, I was able to distill the following from your aswer and the reference source:

1) AI is the broad objective of making computerised device/system exibit human intelligence (Eg. planning, learning from experience & adapting to situations)

2) ML is a means to achieving AI, other means is through explicit programming by building millions of lines of codes with complex rules and decision-trees which is almost impracticable

3) DL is one of the many apparoches to ML, other approaches include decision tree learning, inductive logic programming, clustering, Bayesian networks, etc. Depth is created by using multiple layers as opposed to a single layer hence the term ''Deep''.

4) ANN is a approach to DL which is an algorithm that mimic the biological structure of the brain

5) ML is a way of “training” an algorithm so that it can learnhow.

6) “Training” involves feeding huge amounts of data to the algorithm and allowing the algorithm to adjust itself and improve.


I also learn thus:

AI is categorise into:

-General AI: the computerised device/system would have all of the characteristics of human intelligence

-Narrow AI: the computerised device/system would exhibits some facet(s) of human intelligence, and can do that facet extremely well, but is lacking in other areas. Eg, A machine that’s great at recognizing images, but nothing else, would be an example of narrow AI.


Thank you.

Efiko:
Thanks for the prompt response and the additional reference source provided, I was able to distill the following from your aswer and the reference source:

1) AI is the broad objective of making computerised device/system exibit human intelligence (Eg. planning, learning from experience & adapting to situations)

2) ML is a means to achieving AI, other means is through explicit programming by building millions of lines of codes with complex rules and decision-trees which is almost impracticable

3) DL is one of the many apparoches to ML, other approaches include decision tree learning, inductive logic programming, clustering, Bayesian networks, etc. Depth is created by using multiple layers as opposed to a single layer hence the term ''Deep''.

4) ANN is a approach to DL which is an algorithm that mimic the biological structure of the brain

5) ML is a way of “training” an algorithm so that it can learnhow.

6) “Training” involves feeding huge amounts of data to the algorithm and allowing the algorithm to adjust itself and improve.


I also learn thus:

AI is categorise into:

-General AI: the computerised device/system would have all of the characteristics of human intelligence

-Narrow AI: the computerised device/system would exhibits some facet(s) of human intelligence, and can do that facet extremely well, but is lacking in other areas. Eg, A machine that’s great at recognizing images, but nothing else, would be an example of narrow AI.


Thank you.

Yes you are correct!

A little delay ---> Next lesson is coming up tomorrow.

Thanks.

Frawzey:
Lesson 1:

AI came from one simple question: Can computers learn to think like humans?

Humans can easily identify objects because the brain has “seen” (learned) the images of those objects before – as input, processes it and then identifies the object as a dog, book, stick e.t.c. However, this is extremely difficult for computers. Why? Because computers are primarily programmed for computational results. Computers compute!

A computer can multiply 123736 by 352635 and give the results in nanoseconds but finds it hard to identify a puppy in a picture. To solve this problem, what if we try to replicate how the human brain works in a computer? Just what if…

Enters Neural Network

Now, think about a simple network that takes many input, processes them and gives an output then you have a neural network.

How it works:

Neural networks take in a large number of input, known as training examples, then uses the examples to create rules for recognizing patterns. This means, many pixels of a dog’s image can be ‘fed’ into the computer today to train it, so that when next you ask it to recognize dogs in various pictures, it would give the correct answer. By increasing the number of training examples of different dog pics you show to the computer, it can learn more and so improve its results – it’d even identify a dog in superman’s costume.

Why neural networks in computers?

As explained earlier, simply to replicate how the brain works in computers and enable computers to recognize patterns/objects.

It resembles the brain in two aspects:
a) input is acquired by the network through a learning process. (The learning process is the process whereby the image is shown to the computer so that it learns to identify objects in the image in the future)
b) interconnection strengths between the network are used in results (will explain this later)

I’d continue with the developments on neural networks.

Let me know if you have questions.

[b][/b]can you design a classroom attendance management system using CONVOLUTIONAL NEURAL NETWORK (CNN) WITH PYTHON? IF YES BUZZ ME 07065707659

Wow, nice one @OP following..

To read lesson 1, click here

Lesson 2. Explaining the terms in neural network

Brief introduction
A neural network consists of a input layer, hidden layer (middle layer) and the output layer. The input layer takes in the input (images, files, audio, video etc), passes it to the hidden layer where come processing/learning is done and passed to the output layer for results.



Take a moment to think about this: let's assume you are in a group of 3 friends and you want to tell your 3rd friend you love her. You are the first friend, your second friend, Jay is the middleman or the channel of communication between you and your 3rd friend, Lola.
It means you are the input node(s), Jay is the hidden/middle node and Lola is the output node. Let's say you made a casual whisper to Jay to inform Lola you love her. Jay is reluctant but goes on to say it to Lola.

Its easy for Lola to smile and discard it - meaning the output was not strong enough. Let's assume you call Jay to a corner and tell him with all seriousness that you love Lola and that he should tell Lola the same say you told him.
Jay did exactly what you told him. Lola would likely take it more seriously put that into consideration. She might even reply telling you she loves you too. The words you said are the input, the whispered joking word can be said to have a small weight - its not really serious.
While the seriousness you added to the corner talk had more weight in shaping Lola's response. This is explains the basics of how neural network works. Its takes the product of the input from each layer multiplies it by the weight to give an output.

Now, let's assume Jay told Lola that you "like" her instead of "love". That's an error. You had it mind that he would tell Lola with all seriousness that you love her but he didn't. What you had in mind was an intended output (target) while what Jay said was the actual output.
Mathematically we can calculate this as:
output error = intended output - actual output.

We can moderate this output error by including a learning rate. This learning rate is a figure that we'd multiply with the output error to reduce it so that when next we tell Jay to speak with Lola, the error is minimized. The learning rate is usually a small number.
Before we wrap up, lets assume that Lola has a level or threshold that must be met before she takes people's word into consideration. I mean, there's a level of 'trust' that must met for her to "believe" the speaker.
Mathematically, the threshold that measures the level of 'trust' is called the activation/sigmoid/logistic function.
So it means, Jay must meet that level for her to believe him.
Trust me, we all have it. So it means even for you & Jay, there's also a level of seriousness or trust that must be overcome before you can pass your message across.
Putting this analogy to the neural network, all layers (input, hidden & output layers) have an activation function that must be overcome for a successful message transfer.

Finally, you can improve the output by increasing the number of times you relay your message to Jay as he also speaks to Lola. If you notice that Lola's output was way below our intended result, you can call Jay to the corner again to tell him the same message to tell.
Hoping that it would minimize Jay's error and improve Lola's output.
The number of times we relay our message (input) is called an epoch. We can have 5 epochs so as to improve our output. And the process of relaying the message is called training.

Now lets make a recap of the terms used:
Input layer: is the entrance of the neural network
Hidden layer: where communication (learning) happens
Output layer: where the results happen
Output error: intended output - actual error
Learning rate: moderating factor used to minimize the error
Activation function: threshold that must be overcome for an input to move to the next layer. It takes in the input at every layer.
Epoch: number of times a training is carried out.

Putting it all together, a neural network combines the inputs, learning rate, weights, errors and the activation function to give us the output.

We would be using these terms going forward.

Frawzey:
Okay.

Lesson 2. Explaining the terms in neural network

Brief introduction
A neural network consists of a input layer, hidden layer (middle layer) and the output layer. The input layer takes in the input (images, files, audio, video etc), passes it to the hidden layer where come processing/learning is done and passed to the output layer for results.



Take a moment to think about this: let's assume you are in a group of 3 friends and you want to tell your 3rd friend you love her. You are the first friend, your second friend, Jay is the middleman or the channel of communication between you and your 3rd friend, Lola.
It means you are the input node(s), Jay is the hidden/middle node and Lola is the output node. Let's say you made a casual whisper to Jay to inform Lola you love her. Jay is reluctant but goes on to say it to Lola.

Its easy for Lola to smile and discard it - meaning the output was not strong enough. Let's assume you call Jay to a corner and tell him with all seriousness that you love Lola and that he should tell Lola the same say you told him.
Jay did exactly what you told him. Lola would likely take it more seriously put that into consideration. She might even reply telling you she loves you too. The words you said are the input, the whispered joking word can be said to have a small weight - its not really serious.
While the seriousness you added to the corner talk had more weight in shaping Lola's response. This is explains the basics of how neural network works. Its takes the product of the input from each layer multiplies it by the weight to give an output.

Now, let's assume Jay told Lola that you "like" her instead of "love". That's an error. You had it mind that he would tell Lola with all seriousness that you love her but he didn't. What you had in mind was an intended output (target) while what Jay said was the actual output.
Mathematically we can calculate this as:
output error = intended output - actual output.

We can moderate this output error by including a learning rate. This learning rate is a figure that we'd multiply with the output error to reduce it so that when next we tell Jay to speak with Lola, the error is minimized. The learning rate is usually a small number.
Before we wrap up, lets assume that Lola has a level or threshold that must be met before she takes people's word into consideration. I mean, there's a level of 'trust' that must met for her to "believe" the speaker.
Mathematically, the threshold that measures the level of 'trust' is called the activation/sigmoid/logistic function.
So it means, Jay must meet that level for her to believe him.
Trust me, we all have it. So it means even for you & Jay, there's also a level of seriousness or trust that must be overcome before you can pass your message across.
Putting this analogy to the neural network, all layers (input, hidden & output layers) have an activation function that must be overcome for a successful message transfer.

Finally, you can improve the output by increasing the number of times you relay your message to Jay as he also speaks to Lola. If you notice that Lola's output was way below our intended result, you can call Jay to the corner again to tell him the same message to tell.
Hoping that it would minimize Jay's error and improve Lola's output.
The number of times we relay our message (input) is called an epoch. We can have 5 epochs so as to improve our output. And the process of relaying the message is called training.

Now lets make a recap of the terms used:
Input layer: is the entrance of the neural network
Hidden layer: where communication (learning) happens
Output layer: where the results happen
Output error: intended output - actual error
Learning rate: moderating factor used to minimize the error
Activation function: threshold that must be overcome for an input to move to the next layer. It takes in the input at every layer.
Epoch: number of times a training is carried out.

Putting it all together, a neural network combines the inputs, learning rate, weights, errors and the activation function to give us the output.

We would be using these terms going forward.

Before I go on let me express how happy I am that you made such a thread. Let me just offer my two cents...

Neural networks mustn't always have hidden layers as in the case of the perceptron and the threshold function is called the just the activation function. A sigmoid function is a mathematical function having a characteristic "S"-shaped curve while the logistic function falls under activation functions.

Well done bro .. following

Darivie04:

Before I go on let me express how happy I am that you made such a thread. Let me just offer my two cents...

Neural networks mustn't always have hidden layers as in the case of the perceptron and the threshold function is called the just the activation function. A sigmoid function is a mathematical function having a characteristic "S"-shaped curve while the logistic function falls under activation functions.

Thanks for pointing that out. Really appreciate such response.

..

Sir continue, I'm really learning alot. Thank you so much

Hi All,

Apologies for the delay. I have been engaged with some things.

I'm preparing the next tutorial by trying to simplify it even for a 5 year old and it would be out this week. Meanwhile, if you haven't learned Python at all, and you want to start building the skills for when we need it on this tutorial. Please register and start here: http://www.dataquest.io (highly recommended and free)

Also, feel free to ask question or share ideas.

Thanks.

[quote author=Frawzey post=71742077]Hi All,

Apologies for the delay. I have been engaged with some things.

I'm preparing the next tutorial by trying to simplify it even for a 5 year old and it would be out this week. Meanwhile, if you haven't learned Python at all, and you want to start building the skills for when we need it on this tutorial. Please register and start here: http://www.dataquest.io (highly recommended and free)

Also, feel free to ask question or share ideas.

Thanks.

[/quote

can we have this lesson on WhatsApp?

I really appreciate this AI break down....am here at the right time....thanks for this

Frawzey:
Hi All,

Apologies for the delay. I have been engaged with some things.

I'm preparing the next tutorial by trying to simplify it even for a 5 year old and it would be out this week. Meanwhile, if you haven't learned Python at all, and you want to start building the skills for when we need it on this tutorial. Please register and start here: http://www.dataquest.io (highly recommended and free)

Also, feel free to ask question or share ideas.

Thanks.

hey bro, are there companies in Nigeria where I can do a 6month IT relating to Data science..

Plz can you create a whatsapp forum for this lesson

I read about data science last week when i started learning python. Can i learn both together

Donsheddy:
I read about data science last week when i started learning python. Can i learn both together

Python is the major language for data science. Have at least basic understanding of python syntax then dive into data science.