Neural Networks - Revision history

Iwiseman: /* What are Neural Networks */

2025-01-21T19:45:59Z

What are Neural Networks

← Older revision		Revision as of 19:45, 21 January 2025
Line 20:		Line 20:
	And here we are in 3D looking to the lowest point in the function<br>		And here we are in 3D looking to the lowest point in the function<br>
	[[File:Nn7.png\|500px]]<br>		[[File:Nn7.png\|500px]]<br>
			This walking down to find the lowest point by stepping slowly and testing is known as gradient descent.

Iwiseman: /* What are Neural Networks */

2025-01-17T23:24:02Z

What are Neural Networks

← Older revision		Revision as of 23:24, 17 January 2025
Line 18:		Line 18:
	*a positive slope, move left, if negative slope, move to the right		*a positive slope, move left, if negative slope, move to the right
	[[File:Nn6.png\|500px]]<br>		[[File:Nn6.png\|500px]]<br>
			And here we are in 3D looking to the lowest point in the function<br>
			[[File:Nn7.png\|500px]]<br>

Iwiseman: /* What are Neural Networks */

2025-01-17T22:18:45Z

What are Neural Networks

← Older revision		Revision as of 22:18, 17 January 2025
Line 10:		Line 10:
	So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start<br>		So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start<br>
	[[File:Nn4.png\|500px]]<br>		[[File:Nn4.png\|500px]]<br>
	Next we looked at finding the minimum of the function. Kinda understand what but not why.		Next we looked at finding the minimum of the function. Kinda understand what but not why.<br>
	[[File:Nn5.png\|500px]]<br>		[[File:Nn5.png\|500px]]<br>
	They mentioned<br>		They mentioned<br>

Iwiseman: /* What are Neural Networks */

2025-01-17T22:18:31Z

What are Neural Networks

← Older revision		Revision as of 22:18, 17 January 2025
Line 10:		Line 10:
	So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start<br>		So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start<br>
	[[File:Nn4.png\|500px]]<br>		[[File:Nn4.png\|500px]]<br>
			Next we looked at finding the minimum of the function. Kinda understand what but not why.
			[[File:Nn5.png\|500px]]<br>
			They mentioned<br>
			*taking a random point in the function,
			*calculating the slope of the function where you are,
			*looking for the direction of the slope to determine which direction to move to get the smallest value,
			*a positive slope, move left, if negative slope, move to the right
			[[File:Nn6.png\|500px]]<br>

Iwiseman: /* What are Neural Networks */

2025-01-17T22:05:14Z

What are Neural Networks

← Older revision		Revision as of 22:05, 17 January 2025
Line 8:		Line 8:
	This can be expressed as<br>		This can be expressed as<br>
	[[File:Nn3.png\|500px]]<br>		[[File:Nn3.png\|500px]]<br>
	So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start		So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start<br>
	[[File:Nn4.png\|500px]]<br>		[[File:Nn4.png\|500px]]<br>

Iwiseman: /* What are Neural Networks */

2025-01-17T22:05:00Z

What are Neural Networks

← Older revision		Revision as of 22:05, 17 January 2025
Line 8:		Line 8:
	This can be expressed as<br>		This can be expressed as<br>
	[[File:Nn3.png\|500px]]<br>		[[File:Nn3.png\|500px]]<br>
			So I was expecting to somewhere define what to look for to be certain. E.g. the edges, lack of any pixels etc. But the video went of to speak about training and spoke of the cost function and taking the worst examples and squaring the results. To be honest I will need to buck up my linear maths to make some sense of what was going on. But knowing what you don't know is a start
			[[File:Nn4.png\|500px]]<br>

Iwiseman: Created page with "=Introduction= It is 2025 and time for me to spend more effort in understanding AI a bit more. So I will start, hopefully, at the beginning =What are Neural Networks= Watching the YouTube https://www.youtube.com/watch?v=aircAruvnKk here, it showed an example network which would be used to identify a digit in a 28 x 28 pixel picture. The video talks about about breaking the pixels up and passing them through layers. The layers determine a value for '''the thing you ar..."

2025-01-16T00:40:04Z

Created page with "=Introduction= It is 2025 and time for me to spend more effort in understanding AI a bit more. So I will start, hopefully, at the beginning =What are Neural Networks= Watching the YouTube https://www.youtube.com/watch?v=aircAruvnKk here, it showed an example network which would be used to identify a digit in a 28 x 28 pixel picture. The video talks about about breaking the pixels up and passing them through layers. The layers determine a value for '''the thing you ar..."

New page

=Introduction=
It is 2025 and time for me to spend more effort in understanding AI a bit more. So I will start, hopefully, at the beginning
=What are Neural Networks=
Watching the YouTube [[https://www.youtube.com/watch?v=aircAruvnKk here]], it showed an example network which would be used to identify a digit in a 28 x 28 pixel picture. The video talks about about breaking the pixels up and passing them through layers. The layers determine a value for '''the thing you are looking''' for which comprises of a meaurement + weight + bias 
[[File:Nn1.png|500px]] 
For each neuron in one layer the result of '''the thing you are looking''' is calculated along with the weight and bias
[[File:Nn2.png|500px]] 
This can be expressed as 
[[File:Nn3.png|500px]]