Noisebridge - User contributions [en]

NBDSM

2017-06-06T03:29:40Z

72.182.43.214: /* Prerequisites */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are ~at upper division to graduate level in machine learning and statistical mechanics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* A great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* Anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* The venerable [http://colah.github.io/ colah's blog]
* Stat Mech//Machine Learning conference 2017 at Berkeley: [https://smml.io/ smml:2017]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference
connection.
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:27:06Z

72.182.43.214: /* Links */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are ~at graduate level in machine learning and statistical mechanics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* A great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* Anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* The venerable [http://colah.github.io/ colah's blog]
* Stat Mech//Machine Learning conference 2017 at Berkeley: [https://smml.io/ smml:2017]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference
connection.
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:26:43Z

72.182.43.214: /* Links */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are ~at graduate level in machine learning and statistical mechanics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]
* Stat Mech//Machine Learning conference 2017 at Berkeley: [https://smml.io/ smml:2017]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference
connection.
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:26:23Z

72.182.43.214: /* Links */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are ~at graduate level in machine learning and statistical mechanics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]
* Stat Mech//Machine Learning conference 2017 at Berkeley [https://smml.io/ smml:2017]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference
connection.
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:15:58Z

72.182.43.214: /* Prerequisites */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are ~at graduate level in machine learning and statistical mechanics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference
connection.
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:09:05Z

72.182.43.214: /* Papers */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

Less emphasis on the physics, more emphasis on the stat mech <-> statistical inference
connection.
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:07:00Z

72.182.43.214: /* Papers */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

More stuff
* Mastromatteo - On the typical properties of inverse problems in stat mech - [https://arxiv.org/abs/1311.0190v1 arXiv:1311.0910v1]

NBDSM

2017-06-06T03:04:55Z

72.182.43.214: /* Papers */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==

Good large scale overview of why the stat mech side is important
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

More stuff

NBDSM

2017-06-06T03:03:57Z

72.182.43.214: /* What */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be covering, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]
Good large scale overview of why the stat mech side is important

NBDSM

2017-06-06T02:47:29Z

72.182.43.214: /* Papers */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be learning, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==
* Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]
Good large scale overview of why the stat mech side is important

NBDSM

2017-06-06T02:47:01Z

72.182.43.214: /* Papers */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be learning, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==
Good large scale overview of why the stat mech side is important
Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 arXiv:1301.7115v1]

NBDSM

2017-06-06T02:46:34Z

72.182.43.214: /* Papers */

== What ==

nBDSM is the noiseBridge Deepnet and Statistical Mechanics working group. We meet weekly to learn, teach, and discuss topics at the intersection of AI/deep learning and statistical mechanics. Note that we have a non-trivial overlap with The One, The Only [https://www.noisebridge.net/wiki/DreamTeam Noisebridge DreamTeam].

We're focused on theory. Implementation is fun too, but has its own set of skills that are mostly orthogonal to what we'll be learning, so our focus on it will be light.

== Prerequisites ==

Our discussions are usually at graduate level in machine learning and theoretical physics. To be able to get something out of them, you should have at least undergrad proficiency in

*linear algebra (at the level of D. Lay's book)
*single and multi-variable calculus, and vector calculus (all of Stewart)
*statistics, including bayesian
*statistical mechanics (at the level of [http://mcgreevy.physics.ucsd.edu/s12/index.html McGreevy's MIT lecture notes])

== Links ==
Here are some cool links (you can use these to figure out what to study to get up to speed)

* a great [http://videolectures.net/deeplearning2016_ganguli_theoretical_neuroscience/ talk] by Ganguli at [https://sites.google.com/site/deeplearningsummerschool2016/ last year's deep learning summer school] in Montreal.
* anything recent by [https://arxiv.org/find/stat/1/au:+Ganguli_S/0/1/0/all/0/1 Ganguli] at the [https://ganguli-gang.stanford.edu/ Neural Dynamics and Computation Lab] as well.
*[https://calculatedcontent.com/ Calculated Content]
* the venerable [http://colah.github.io/ colah's blog]

== Papers ==
Good large scale overview of why the stat mech side is important
Advani et. al. - Stat mech of complex neural systems and high dimensional data - [https://arxiv.org/abs/1301.7115v1 q-bio:1301.7115v1]