Machine Learning Meetup Notes: 2009-03-11 - Revision history

SpammerHellDontDelete: Add Ping's perceptron (in Python)

2009-03-19T02:19:35Z

Add Ping's perceptron (in Python)

← Older revision		Revision as of 19:19, 18 March 2009
Line 16:		Line 16:
	* [http://github.com/david415/ml-py/tree/master Python implementation by David Stainton]		* [http://github.com/david415/ml-py/tree/master Python implementation by David Stainton]
	* [[User:Kaufman/LISP_Perceptron\|LISP!]] by John Kaufman		* [[User:Kaufman/LISP_Perceptron\|LISP!]] by John Kaufman
			* [[User:Ping/Python_Perceptron]] by [[User:Ping]]

	Everyone should upload their code!		Everyone should upload their code!

David415: /* Code people wrote */

2009-03-19T01:59:54Z

Code people wrote

← Older revision		Revision as of 18:59, 18 March 2009
Line 14:		Line 14:
	* Ruby by Zhao [https://www.noisebridge.net/wiki/Machine_Learning_Meetup_Notes_Ruby_Zhao]		* Ruby by Zhao [https://www.noisebridge.net/wiki/Machine_Learning_Meetup_Notes_Ruby_Zhao]
	* C by Cristian [https://www.noisebridge.net/wiki/User:Cortiz]		* C by Cristian [https://www.noisebridge.net/wiki/User:Cortiz]
	* [~~https~~://~~www~~.~~noisebridge.net~~/~~wiki~~/~~davids_perceptron.pl~~ Python implementation by David Stainton]		* [http://github.com/david415/ml-py/tree/master Python implementation by David Stainton]
	* [[User:Kaufman/LISP_Perceptron\|LISP!]] by John Kaufman		* [[User:Kaufman/LISP_Perceptron\|LISP!]] by John Kaufman

Cmaier at 23:57, 17 March 2009

2009-03-17T23:57:39Z

← Older revision		Revision as of 16:57, 17 March 2009
Line 25:		Line 25:
	Can you build a training set for an OR gate, and train it? What other operators can you implement this way? All you need to do is build a new training set and try training, which is pretty awesome if you think about it. (Hint: What does "separability" mean, and how is it relevant?)		Can you build a training set for an OR gate, and train it? What other operators can you implement this way? All you need to do is build a new training set and try training, which is pretty awesome if you think about it. (Hint: What does "separability" mean, and how is it relevant?)

	Let's say we wanted to output smooth values instead of just 0 or 1. What wouuld you need to change in your evaluation step to get rid of the thresholding? What wouuld you need to change about learning to allow your neuron to learn smooth functions? (Hint: in a smooth output function, we want to change the amount of training we do by how far we were off, not just by which direction we were off.)		Let's say we wanted to output smooth values instead of just 0 or 1. What wouuld you need to change in your evaluation step to get rid of the thresholding? What wouuld you need to change about learning to allow your neuron to learn smooth functions? (Hint: in a smooth output function, we want to change the amount of training we do by how far we were off, not just by which direction we were off.)

			''One answer: [https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks_2009MAR17.pdf PDF of Mathematica workspace]''

	What if we wanted to do something besides multiple each input by its weight? What if we wanted to do something crazy, like take the second input, square it, and multiply _that_ by the weight? That is: what if we wanted to make the output a polynomial equation instead of a linear one, where each input is x^1, x^2, etc, with the weights as their coefficients? What would need to change in your implementation? What if we wanted to do even crazier things, like bizarre trig functions?		What if we wanted to do something besides multiple each input by its weight? What if we wanted to do something crazy, like take the second input, square it, and multiply _that_ by the weight? That is: what if we wanted to make the output a polynomial equation instead of a linear one, where each input is x^1, x^2, etc, with the weights as their coefficients? What would need to change in your implementation? What if we wanted to do even crazier things, like bizarre trig functions?

SpammerHellDontDelete: /* Machine Learning Meetup Notes: 2009-03-11 */

2009-03-17T19:07:35Z

Machine Learning Meetup Notes: 2009-03-11

← Older revision		Revision as of 12:07, 17 March 2009
Line 3:		Line 3:

	We made perceptrons. To learn how, you should go to Wikipedia [http://en.wikipedia.org/wiki/Perceptron]		We made perceptrons. To learn how, you should go to Wikipedia [http://en.wikipedia.org/wiki/Perceptron]

			Also reasonably good: [http://www.cs.usyd.edu.au/~irena/ai01/nn/travtute.htm Neural Networks Tutorial], from the Introduction to Part 5.

	===Code people wrote===		===Code people wrote===

Cmaier at 06:18, 14 March 2009

2009-03-14T06:18:22Z

← Older revision		Revision as of 23:18, 13 March 2009
Line 1:		Line 1:
	==Machine Learning Meetup Notes: 2009-03-11==		==Machine Learning Meetup Notes: 2009-03-11==
			[[Image:IMG_4478.JPG\|816px]]

	We made perceptrons. To learn how, you should go to Wikipedia [http://en.wikipedia.org/wiki/Perceptron]		We made perceptrons. To learn how, you should go to Wikipedia [http://en.wikipedia.org/wiki/Perceptron]

Elgreengeeto at 16:58, 13 March 2009

2009-03-13T16:58:53Z

← Older revision		Revision as of 09:58, 13 March 2009
Line 7:		Line 7:
	* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)		* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)
	* [[Machine Learning Meetup Notes Perceptron Matlab\|Matlab/Octave perceptron]] by Jean		* [[Machine Learning Meetup Notes Perceptron Matlab\|Matlab/Octave perceptron]] by Jean
	* Python by Skory		* [[User:Elgreengeeto/Python_Perceptron\|Python]] by [[User:Elgreengeeto\|Skory]]
	* [[RachelPerceptronPython\|extremely naive Python]] by Rachel		* [[RachelPerceptronPython\|extremely naive Python]] by Rachel
	* Ruby by Zhao [https://www.noisebridge.net/wiki/Machine_Learning_Meetup_Notes_Ruby_Zhao]		* Ruby by Zhao [https://www.noisebridge.net/wiki/Machine_Learning_Meetup_Notes_Ruby_Zhao]

Jbm: /* Code people wrote */

2009-03-13T13:13:09Z

Code people wrote

← Older revision		Revision as of 06:13, 13 March 2009
Line 6:		Line 6:

	* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)		* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)
	* Matlab/Octave by Jean		* [[Machine Learning Meetup Notes Perceptron Matlab\|Matlab/Octave perceptron]] by Jean
	* Python by Skory		* Python by Skory
	* [[RachelPerceptronPython\|extremely naive Python]] by Rachel		* [[RachelPerceptronPython\|extremely naive Python]] by Rachel

Jbm: /* Machine Learning Meetup Notes: 2009-03-11 */

2009-03-13T05:49:02Z

Machine Learning Meetup Notes: 2009-03-11

← Older revision		Revision as of 22:49, 12 March 2009
Line 3:		Line 3:
	We made perceptrons. To learn how, you should go to Wikipedia [http://en.wikipedia.org/wiki/Perceptron]		We made perceptrons. To learn how, you should go to Wikipedia [http://en.wikipedia.org/wiki/Perceptron]

	~~We had the following success:~~		===Code people wrote===

	* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)		* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)
Line 15:		Line 15:

	Everyone should upload their code!		Everyone should upload their code!

			===Follow-on notes===

			Now, if you look at your weights and think about what they mean, you'll notice something odd. At the end, the weights aren't equal! We trained a NAND gate, so every input should have an equal opportunity to change the output, right? Given that last leading question, what would you expect the ideal weights to be? Do the learned weights match that expectation? Why? (Hint: What does "overfitting" mean, and how is it relevant?)

			Can you build a training set for an OR gate, and train it? What other operators can you implement this way? All you need to do is build a new training set and try training, which is pretty awesome if you think about it. (Hint: What does "separability" mean, and how is it relevant?)

			Let's say we wanted to output smooth values instead of just 0 or 1. What wouuld you need to change in your evaluation step to get rid of the thresholding? What wouuld you need to change about learning to allow your neuron to learn smooth functions? (Hint: in a smooth output function, we want to change the amount of training we do by how far we were off, not just by which direction we were off.)

			What if we wanted to do something besides multiple each input by its weight? What if we wanted to do something crazy, like take the second input, square it, and multiply _that_ by the weight? That is: what if we wanted to make the output a polynomial equation instead of a linear one, where each input is x^1, x^2, etc, with the weights as their coefficients? What would need to change in your implementation? What if we wanted to do even crazier things, like bizarre trig functions?

Kaufman: /* Machine Learning Meetup Notes: 2009-03-11 */ Adding link to LISP

2009-03-13T05:36:41Z

Machine Learning Meetup Notes: 2009-03-11: Adding link to LISP

← Older revision		Revision as of 22:36, 12 March 2009
Line 12:		Line 12:
	* C by Cristian [https://www.noisebridge.net/wiki/User:Cortiz]		* C by Cristian [https://www.noisebridge.net/wiki/User:Cortiz]
	* [https://www.noisebridge.net/wiki/davids_perceptron.pl Python implementation by David Stainton]		* [https://www.noisebridge.net/wiki/davids_perceptron.pl Python implementation by David Stainton]
			* [[User:Kaufman/LISP_Perceptron\|LISP!]] by John Kaufman

	Everyone should upload their code!		Everyone should upload their code!

Rachel at 06:22, 12 March 2009

2009-03-12T06:22:45Z

← Older revision		Revision as of 23:22, 11 March 2009
Line 7:		Line 7:
	* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)		* Mathematica, by Christoph ([https://www.noisebridge.net/wiki/Image:NoisebridgeNeuralNetworks.pdf PDF], because noisebridge is ''a little'' too anti-commercial)
	* Matlab/Octave by Jean		* Matlab/Octave by Jean
	* Python by Skory ~~and~~ Rachel		* Python by Skory
			* [[RachelPerceptronPython\|extremely naive Python]] by Rachel
	* Ruby by Zhao [https://www.noisebridge.net/wiki/Machine_Learning_Meetup_Notes_Ruby_Zhao]		* Ruby by Zhao [https://www.noisebridge.net/wiki/Machine_Learning_Meetup_Notes_Ruby_Zhao]
	* C by Cristian [https://www.noisebridge.net/wiki/User:Cortiz]		* C by Cristian [https://www.noisebridge.net/wiki/User:Cortiz]