Khaula Nauman > Recent Status Updates

The book was going great so ofcourse mary had to sneak in her islamophobe and racist views.
And her utter biasness to the white race and christianity. Great!

"There was always scope for fear so long as anything I loved remained behind."
the writing is so so good
and to think show wrote this when she was 18?!

"In the early days of AI research people hoped that the effort to build an AI would also help us understand the principles behind intelligence and, maybe, the functioning of the human brain. But perhaps the outcome will be that we end up understanding neither the brain nor how artificial intelligence works!"
this cracked me up

Usually, when programming we believe that solving a complicated problem like recognizing the MNIST digits requires a sophisticated algorithm. But even the neural networks in the Wan et al paper just mentioned involve quite simple algorithms, variations on the algorithm we've seen in this chapter.

The lesson to take away from this is that debugging a neural network is not trivial, and, just as for ordinary programming, there is an art to it. You need to learn that art of debugging in order to get good results from neural networks. More generally, we need to develop heuristics for choosing good hyper-parameters and a good architecture.

Also the little pieces of art work at the beginning of each part are amazing! Such a nerdy and cool move

Im done with the first part of the book and it was so well written it was depressing at times. You would think one would find reading about someone who's living an invisible life would be fun but the writer is so good with words that i almost closed the book because it felt so heavy. The way writer has made the point "you dont realise the value of something until it is taken from you" is amazing.

i now know what
- a neural network is
- are preceptor neurons
- are sigmoid neurons
- a sigmoid function is and why sigmoid
- are feedforward neural networks and recurrent ones
- a cost function is (i think)
- how gradient descent helps us minimize our cost function and helps us get closer to finding the correct output
- a stochastic gradient descent is and what is on-line learning

"Instead of explicitly laying out a circuit of NAND and other gates, our neural networks can simply learn to solve problems, sometimes problems where it would be extremely difficult to directly design a conventional circuit."
from a wonders-of-modern-science prespective it sounds amazing! revolutionary even
but then theres also a part in me that goes "have we really done the right thing just because we could"