How Convolutional Neural Networks Work • Hacker News Board

Re: How Convolutional Neural Networks Work

#51

Post by eli_gottlieb » Tue, Sep 27, 2016, 3:00 PM UTC

banned4life wrote: post #49

armandtamzarian wrote: post #27

Great post. I like how he didn't go into too much detail on the math of backprop etc. I find the conceptual understanding of ML is more interesting as a lay person.

If you google "Hinton machine learning" on youtube, you will find hinton's lecture's they are non-mathematical, he is a psychologist/math guy, and he is the inventor of almost all this stuff, backprop, drop-out, You will find his lectures to be very entertaining and easy to understand, being a psychologist whose desire is to make a computer operate like a human brain, he's more interested in how the brain actually wo…

>You will find his lectures to be very entertaining and easy to understand, being a psychologist whose desire is to make a computer operate like a human brain, he's more interested in how the brain actually works, than hacking ML code. > >Hinton describes backprop, why he invented it, and exactly how it emulates the way the human brain works.

Of course, basically no actual neuroscientists or cognitive scientists think the brain actually works via supervised backpropagation. So he actually has a bit of a holy war going on with the people who properly work on human learning rather than machine learning.

Re: How Convolutional Neural Networks Work

#52

Post by sidarape » Tue, Sep 27, 2016, 6:01 PM UTC

spiderfarmer wrote: post #10

Question: I have a database with 1.000.000 vehicle pictures, organized by make and model. What would be the easiest way to play with this data, so that I can train it to predict the make / model? I don't want to reinvent the wheel now so much tutorials are written and software is being released. What would be the easiest way to start?

As I said in another thread, I used that (https://www.tensorflow.org/versions/r0.9/how_tos/image_retra...) which seems to work well. I think especially with your problem since it is similar to the type of classification of ImageNet.

Re: How Convolutional Neural Networks Work

#53

Post by misiti3780 » Tue, Sep 27, 2016, 8:01 PM UTC

stared wrote: post #12

spiderfarmer wrote: post #10

Question: I have a database with 1.000.000 vehicle pictures, organized by make and model. What would be the easiest way to play with this data, so that I can train it to predict the make / model? I don't want to reinvent the wheel now so much tutorials are written and software is being released. What would be the easiest way to start?

With that number you can train a model from scratch. Alternatively, you can retrain the last layers (it requires much less data). The easiest way is to use some well-known architecture (e.g. VGG16) and go. See: https://github.com/leriomaggio/deep-learning-keras-euroscipy...

do you have any examples of scripts/examples where only specific layers of a network are being trained?

Re: How Convolutional Neural Networks Work

#54

Post by alien_ » Thu, Sep 29, 2016, 10:57 AM UTC

anantzoid wrote: post #40

lettergram wrote: post #18

Earlier quoted context omitted.

I setup an automated script to setup a AWS g2 instance, train my neural net using tensorflow, copy my model to my personal computer, and spin down. It costs like $5-$10 to train/test most neural network models. My most expensive model cost like $100 and required a ton of time and resources. It took like 4 days or something. You really dont need $2k workstation.. Of course, for personal use I do have a gtx 1080 becaus…

Spot instances cost way cheaper. The only downside is you need to create an AMI everytime before termination. But, also, AWS g2 has NVIDIA Grid K50 with 4GB memory, so it's not very good with performance.

The AMI creation is only needed if you store data on the machines, which you shouldn't do anyway, not even with on-demand ones.

You should always try to keep the instances stateless and store any data outside the instances, such as on S3 or EFS.