Thanks Robert for putting this together. Coming from PyTorch ecosystem. What is the actual requirement for this course? Would a smattering knowledge of ES6 do? Been leching at browser based implementations since Karpathy demoed his CNNs a few years ago but just havent had enough motivation and courage to pickup JS. Perhaps my main reson for anxiety is the confusing JS ecosystem.Also what are some real world use cases for training and deploying NNs on the browser rather than training and deploying it on a tradional cloud backend environment?
Neural networks in JavaScript – free 19-part course
31–40 of 74 posts
Re: Neural networks in JavaScript – free 19-part course
#32Is there a Numpy equivalent for JS yet? How easy is it to use (considering that JS doesn't have operator overloading)?
Re: Neural networks in JavaScript – free 19-part course
#33Awesome! Bonus point for doing a js course
Re: Neural networks in JavaScript – free 19-part course
#34Why the heck Javascript?
Why not? It's extremely popular, fast and portable.
Also, it's hard to beat the browser for creating a quick visualization/UI for your code. Especially for an online course like this.
I think we're at a point where you'd have to justify why you didn't use Javascript for a learning course.
Re: Neural networks in JavaScript – free 19-part course
#35Earlier quoted context omitted.
There is NO save on computation cost. CPU is slow for NN whatever language you are using. OP has a point, if I want to learn PRACTICAL front end programming, I will choose javascript, not Python. Same for Neural networks, just switch the place.
What's wrong with js for neural networks? JS/V8 is faster than python, not accounting for python bindings to native NN libs that may as well be bound to js.
JS/V8 may beat Python in general operations but definitely not in math specialized libraries. A lot of python packages support OpenBLAS and AVX/FMA by default which gives huge boosts to math/tensor operations. Correct me if I'm wrong, I don't think the js ecosystem is quite there yet except for experimental projects.
Re: Neural networks in JavaScript – free 19-part course
#36why would you do ML in JS?
Re: Neural networks in JavaScript – free 19-part course
#37I just watched the reinforcement learning video and was very confused -- where did the reinforcement learning happen? I thought reinforcement learning was giving an agent positive / negative signals to learn without example output data, but in the video the network was just retrained with more data? Is it an overloaded term maybe?
Re: Neural networks in JavaScript – free 19-part course
#38Thanks Robert for putting this together. Coming from PyTorch ecosystem. What is the actual requirement for this course? Would a smattering knowledge of ES6 do? Been leching at browser based implementations since Karpathy demoed his CNNs a few years ago but just havent had enough motivation and courage to pickup JS. Perhaps my main reson for anxiety is the confusing JS ecosystem.Also what are some real world use cases…
Real world use cases might be; Classifying the users mood from mouse movement, classifying the microphone audio. I.e. process real time data that might be too large to upload.
I personally haven't seen any NNs being used in browser apps, but there are plenty of existing mobile apps that has NNs to classify audio/video/etc directly on the device.
Re: Neural networks in JavaScript – free 19-part course
#39Thanks Robert for putting this together. Coming from PyTorch ecosystem. What is the actual requirement for this course? Would a smattering knowledge of ES6 do? Been leching at browser based implementations since Karpathy demoed his CNNs a few years ago but just havent had enough motivation and courage to pickup JS. Perhaps my main reson for anxiety is the confusing JS ecosystem.Also what are some real world use cases…
afaik it's mostly for cool demos and educational purposes, or extremely latency intensive applications that funny require large models.
for most deep learning models, training on the client is completely unreasonable, as they require weeks of training even on multi thousand $ pro equipement.
For training, tiny metalearning models are the only reasonable thing to train on the clients in most useful scenarios, as they are pretrained to take as few examples as possible to train on a specific task (see MAML).
For inference, aside from educational applications, the only potential advantage of in browser over in server is the lower latency. the main disadvantages are that you need to send the model to the client (multiple MB), with the longer loading time and potential problems with intellectual property this entails. maybe for some extremely small models in very latency driven applications, it can be worth it.
So, overall, either educational purposes, training and use of latency hungry tiny metalearning models or inference with tiny pretrained latency hungry models, like computer vision on webcam sort of deal
Re: Neural networks in JavaScript – free 19-part course
#40Hey guys! I'm the creator of the course and lead developer of brain.js and would love to answer any questions you may have.
It took me a while to realize I wasn't just watching a static video and that I could actually interact with the code! Very well done and nice pacing/voiceover.