HNHacker News
TopNewBestAskShowJobs

Seanny123

198 karma · joined October 26, 2015

github.com/Seanny123
submissionscomments
Seanny123··on The Nengo Neural Simulator
Other student from the lab here.

You could, but it might not be particularly useful. They already have a really good simulation environment and ways to connect it to virtual environments. It would be useful if you wanted to extend the model with further neural populations!

Seanny123··on The Nengo Neural Simulator
Another student from the lab here.

> unfortunately docs aren’t helping at all

Yeah, the docs really aren't the ideal entry point. Instead, I'd recommend installing the [Nengo GUI](https://github.com/nengo/nengo-gui) and going through the built-in tutorial.

> 1. Where can I find a diagram of neuron you use?

We use a bunch of different neurons [1], but the default one is the Spiking LIF. It's really common in computational neuroscience.

> 2. Where can I find a diagram of network you use (for simple example)?

Check out this video example in the Nengo GUI https://youtu.be/UVeIPKnQAL4

> 3. What is an example of simple learning algorithm for above?

There's a tutorial in the Nengo GUI, but there's also a few Jupyter Notebook examples: https://www.nengo.ai/nengo/examples.html#learning

[1] See related psychology.stackexchange.com question https://psychology.stackexchange.com/a/9131/4397

Seanny123··on How to build a brain – An introduction to neurophysiology for engineers
To be clear, this article is about neural computation, while Joscha has chosen to ignore the constraints imposed by this computational paradigm.
Seanny123··on How to build a brain – An introduction to neurophysiology for engineers
> There are fundamental questions left unanswered: What information do neurons represent? How do neurons connect to achieve that? How are these representations learned? Neuroscience offers partial answers and algorithmic ideas, but we are far from a complete theory conclusively backed by observations.

Calling the answers "partial" is fair, but I feel like the author understates the number of observations backing typical neural models? The lab I belong to created Spaun, which admittedly uses a pretty simple neuron model, but still matched a ton of neural and behavioural data! There's also Leabra, which I have some qualms with, but still has a pretty large collection of results.

Seanny123··on Ask HN: As a data scientist, what should be in my toolkit in 2018?
I would love some examples where R makes it easier to get answers than Python. Probably would make good Pandas2 issue too!
Seanny123··on Mothers who regret having children are speaking out
This article seemed more like the documentation of a cultural phenomenon (mothers able to publicly admit regret) than a sociological study. But I still want to know why mothers regret having children. The comments seemed to be filled with uncharitable explanations, but are there any publications (other than the isreali one) that summarises the reasons for regret?
Seanny123··on Reservoir computing using dynamic memristors for temporal information processing
Whelp. I was super wrong. I had predicted I wouldn't see memristor-based neuromorphic hardware in the next 10 years.

That being said, I feel like they're over-selling the capabilities of reservoir computing. Yeah, [you can stack them](https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2016...) and get pretty high accuracy on a few tasks, but it's still not competitive with traditional Deep Learning.

Seanny123··on Chisel: Constructing Hardware in a Scala Embedded Language
How does this compare to the various other languages that compile to Verilog?

Update: read the paper and they cover a few examples in it. Don't have enough domain knowledge to judge whether the claims are accurate, nor whether they generalise to something like clash-lang.

Seanny123··on Patterns Failed. Why? Should We Care?
The book referenced at the end, called Domain-Driven Design, has mixed reviews. Does anyone understand why a lot of people found it disorganised and vague?
Seanny123··on Robot Operating System 2.0: Ardent Apalone Release
Did they fix the build system or are they still going to use the weird catkin build system? I read the article, but it didn't mention it. I ask, because it has been consistently the most difficult part of using ROS for myself and everyone I know. Alternatively, is the difficulty I've experienced more of an indication of build systems being complicated things?
Seanny123··on WebAssembly support now shipping in all major browsers
This is precisely what I'm waiting for as well. I want to run the Nengo neural simulator in the browser, so I can share my research easily, but it looks like I'll have to wait a few years.
Seanny123··on A Theory of Sequence Memory in Neocortex
But HTM (the learning rule mentioned in this article) isn't biologically plausible, despite trying to be Hebbian. See this discussion on my lab's forum: https://forum.nengo.ai/t/hierarchical-temporal-memory-vs-nef...

Edit: linked to specific post in forum thread instead of the whole thread

Seanny123··on ZeroMe – Decentralized Microblogging on ZeroNet
> Technically, decent idea. Realistically, you're hosting the stuff people don't want to pay to host.

Very personally, I see it as contributing a small amount of a very non-scarce resource (bandwidth, disk space, computing power) so that I have greater control over the platform I'm using. I loved both Twitter and Medium, but the corporations that run them have different ideas about what they're for. I see web decentralised about letting the user choose their experience instead of having it enforced on them.

Seanny123··on Brain vs. Deep Learning (2015)
That's basically what the entire field of computational/theoretical neuroscience is trying to figure out right now. What's being computed? What's the right level of abstraction? Basically, it depends on what you're modelling: https://www.ncbi.nlm.nih.gov/pubmed/24709593
Seanny123··on Brain vs. Deep Learning (2015)
The math this guy performs is so questionable and his idea that Deep Learning is the pinnacle of biologically plausible cognitive modelling is incorrect. I write about this [in a blog post](https://medium.com/@seanaubin/deep-learning-is-almost-the-br...).

tl;dr doing pure Deep Learning (also known as connectionist) models of the brain limits your tools in a bad way. Using tools from Dynamicism and Symbolicism is better. As proof, check out Spaun, the world's largest functioning brain model.

Note: I mostly just disagree with him philosophically, in terms of his reasoning because it's overlooking some evidence. Don't really have an option on his conclusion. Probably agree with him more than I disagree with him.

Seanny123··on Intel Introduces Neuromorphic Test Chip
Huh, apparently. This will be an interesting conversation at the next lab meeting.
Seanny123··on Intel Introduces Neuromorphic Test Chip
> Nothing works nearly as well by comparison.

Depends on what you mean by "well". It would be foolish of me to deny the advances of deep learning. However, there are limitations and the NEF can act as a bridge in those cases. For example, if you want:

1. To approximate a dynamic system 2. To use symbolic computation 3. Use the neural networks as an initial guess at a solution to a problem and then want to use gradient descent to figure out the actual solution

I talk about using NEF as a bridge in [this blog post](https://medium.com/@seanaubin/deep-learning-is-almost-the-br...), if you're curious. Unfortunately, I don't know of any examples using the "initial guess" paradigm that I describe, but that's more of a "not enough people using Nengo" problem.

Seanny123··on Intel Introduces Neuromorphic Test Chip
> there's no need for machine learning, neural networks or etc.

There is if: 1. You want an energy-efficient distributed representation of the function. 2. You want to use the function as an initial guess and then learn online afterwards.

Seanny123··on Intel Introduces Neuromorphic Test Chip
I'm from the lab that you're citing with those links and I'm kind of amazed you're so up to date with our research. Why do you know so much about Nengo? Are you actually one of my lab-mates, but I just can't identify you from your username?
Seanny123··on Intel Introduces Neuromorphic Test Chip
> Does not need to be trained? The writer maybe wanted to say it does not need to be programmed in the traditional way.

There are two ways to build spiking neural net architectures without training. The [Neural Engineering Framework](https://medium.com/@seanaubin/a-way-around-the-coming-perfor...) and [Deneve's approach which I'm more uncertain about](https://forum.nengo.ai/t/robustness-of-deneves-networks/320?...).

To be clear, when I say "training" in this context, I mean they don't require iterative rounds of stochastic gradient descent. They just need to be given the function that you want to approximate and then they're done.

Seanny123··on Windows for Linux Nerds
Seriously. This has been the one major stalling point for me as well. Setting up a Python environment and installing programs with Chocolatey were trivial, but the damn PowerShell terminal is ugly as sin.
Seanny123··on A tale of two Canadas: Where you grew up affects your income in adulthood
Not to mention the Sudbury and Waterloo area which is super left-wing and unionist. I mean, anecdotal, but I feel like it's okay to counter an anecdote with an anecdote in this case? Further analysis would require access to the data being shown here and cross referencing it with the outcome of past elections.
Seanny123··on Facebook Trains ImageNet in 1 Hour
very personally, clever means "well, that would have taken me a long time to figure out and code properly"
Seanny123··on Facebook Trains ImageNet in 1 Hour
tl;dr they found a clever way to spread the training across 256 GPUs by synchronising the stochastic gradient descent
Seanny123··on Exploring LSTMs
Is the code for generating the reactions from the LSTM hidden units posted anywhere? That was the best part for me and I'd love to use it in my own projects.
Seanny123··on [dead]
Thank you so much for pointing me to web.skype.com. I didn't know this existed and it solves so many problems for me.
Seanny123··on What intelligent machines need to incorporate from the neocortex
I think it's more important to choose the right level of detail for what you're modelling. This is covered in "The Use and Abuse of Large Scale Brain Models" [1].

[1] https://github.com/arvoelke/delay2017/blob/master/delay2017....

Seanny123··on What intelligent machines need to incorporate from the neocortex
Nice references! I have some criticism of "Toward an Integration of Deep Learning and Neuroscience" which I've talked to the authors about. I felt like they downplayed the importance of integration between neuroscience and machine learning [1], while over-playing the biological plausibility of Deep Learning [2]. I'm also uncomfortable with the characterization of Neuromorphic computing as "Deep Learning on a Chip", as this dismisses the possibility of online learning and neural dynamic systems [3], which I think are necessary for truly intelligent systems.

As for Liquid State Machines, those evolved into Reservoir Computing and Echo State Machines. If you want to read more about them, I would recommend this paper comparing them to the Neural Engineering Framework [4] (with code!) to get a good idea of the state of the field.

[1] https://medium.com/@seanaubin/deep-learning-is-almost-the-br...

[2] https://cogsci.stackexchange.com/q/16269/4397

[3] https://medium.com/@seanaubin/a-way-around-the-coming-perfor...

[4] https://github.com/arvoelke/delay2017/blob/master/delay2017....

Seanny123··on What intelligent machines need to incorporate from the neocortex
> I was disappointed to find out that numenta does not really have collaborations with neuroscientists to test or adapt their theories. Their theories in general are not well known to computational neuroscientists either. In that sense, i m not even sure about the authority of numenta on neocortical theories.

Numenta isn't biologically plausible [1], so although the resulting networks might be mappable to the brain in the same manner as Deep Learning and FORCE trained networks, there's no way to map the learning period onto brains.

[1] https://forum.nengo.ai/t/hierarchical-temporal-memory-vs-nef...

Seanny123··on Extracting Chinese Hard Subs from a Video, Part 1
Found a paper! Yes, it is better. Maybe not for this specific application and given there's no pre-trained network available, I can totally understand the choice made. https://www.semanticscholar.org/paper/The-recognition-of-Chi...
← PreviousPage 2 of 4Next →