Data Analysis From Scratch With Python: Step By Step Guide

X = np.array([ [0,0,1],[0,1,1],[1,0,1],[1,1,1] ])
y = np.array([[0,1,1,0]]).T
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1
for j in xrange(60000):
l1 = 1/(1+np.exp(-(np.dot(X,syn0))))
l2 = 1/(1+np.exp(-(np.dot(l1,syn1))))
l2_delta = (y - l2)*(l2*(1-l2))
l1_delta = l2_delta.dot(syn1.T) * (l1 * (1-l1))

---

syn1 += l1.T.dot(l2_delta)
syn0 += X.T.dot(l1_delta)
From 
https://iamtrask.github.io/2015/07/12/basic-
python-network/
It’s a very simple example. In real world, artificial neural networks would look
long and complex when written from scratch. Thankfully, how to work with
them is becoming more “democratized,” which means even people with limited
technical backgrounds would be able to take advantage of them.

---

16. Natural Language Processing
Can we make computers understand words and sentences? As mentioned in the
previous chapter, one of the goals is to match or surpass important human
capabilities. One of those capabilities is language (communication, knowing the
meaning of something, arriving at conclusions based on the words and
sentences).
This is where Natural Language Processing or NLP comes in. It’s a branch of
artificial intelligence wherein the focus is on understanding and interpreting
human language. It can cover the understanding and interpretation of both text
and speech.
Have you ever done a voice search in Google? Are you familiar with chatbots
(they automatically respond based on your inquiries and words)? What about
Google Translate? Have you ever talked to an AI customer service system?
It’s Natural Language Processing (NLP) at work. In fact, within a few or several
years the NLP market might become a multi-billion dollar industry. That’s
because it could be widely used in customer service, creation of virtual assistants
(similar to Iron Man’s JARVIS), healthcare documentation, and other fields.
Natural Language Processing is even used in understanding the content and
gauging sentiments found in social media posts, blog comments, product
reviews, news, and other online sources. NLP is very useful in these areas due to
the massive availability of data from online activities. Remember that we can
vastly improve our data analysis and machine learning model if we have
sufficient amounts of quality data to work on.