Відео

I have exactly the same setup, but I don't have the "Figure options" button. Do you know how to enable it?

How can someone be so awesome...

I set up everything properly. In PyCharm all works perfectly. In mobile phone App too... But! - my training data in mobile App and data in python are not the same. I'll wait one day. Maybe they have one update in a day or sth

Nice video sir, Started python after 2-3 weeks and was having some doubts using this API , your video helped greatly

There is a mistake at 2:58. The error in the model for training should actually be less than the test set because it overfits to the training set and minimizes the error in the test set.

I didn't understand your language but you served the purpose Thanks a lot

great video

Can you provide the code in comments

i got this error when trying to open the csv file UnicodeDecodeError: 'utf-8' codec can't decode byte 0xae in position 265: invalid start byte

you helped me thank you.

Come on finish it of DB

If you have an up-to-date pandas installation you can just do a.plot(y='Close') without the need to explicitly create b or import matplotlib.

Awesome, nice explanation

do you know. you helped me thank you.

how to apply it for the column give me the code

My data set is consisting of 20,000 articles but I want to train only the first 100 do u know the command??

hello there, i am gettin this error ("message": "request requires x-app-id and x-app-key headers") i gave all the headers correctly though.

Great video, I learned a lot. "Thank you for making it.

Awesome!! That's what exactly I needed to know how to make interactive plots in Python

Thank you I need that QT!

Great Xplanations anchor here~

Whoal ny git link ?

There are alternatives to back propagation. The simple evolution algorithm Continuous Gray Code Optimization works very well. You can find the paper online. The mutation operator is random plus or minus a.exp(-p.rnd()). If the neural network weight is constrained between -1 and 1 then a=2 to match the interval. rnd() returns a uniform random between 0 and 1. p is the so called precision and is a problem dependent positive number. It is easy to distribute training over many compute devices. Each device gets the full neural model and part of the training data (which can be local and private.) Each device is sent the same short sparse list of mutations and returns the cost for its part of the training data. The costs are summed and if an improvement an accept message is sent to each device else a reject message. Not much data is moving around per second. The devices could be anywhere on the internet, all around the place. Of course with evolution the faster the neural net the better. Fast Transform fixed filter bank neural nets are a good choice. There is some blog about them

Discrete convolutions, weighted sums and fast transforms like FFT are dot products. Max pooling is switching. ReLU is a switch🤔 f(x)=x is connect, f(x)=0 is disconnect. A light switch in your house is binary on off yet connects or disconnects a continuously variable AC voltage signal. The dot product of a number of dot products is still a dot product. When all the switch states become known in a ReLU net the net collapses to a simple matrix. There is a linear mapping from the input vector to the output vector. There are a lot of metrics you can apply and further math that can be done.

my left ear really enjoyed this

Really helpful thank you