You were just hired by MetaMind. MetaMind is expanding rapidly, and you decide t

Question

You were just hired by MetaMind. MetaMind is expanding rapidly, and you decide to use your machine learning skills to assist them in their attempts to hire the best. To do so, you have the following available to you for each candidate i in the pool of candidates T: (i) Their GPA,) Whether they took Data Mining course and achieved an A, (iii) Whether they took Algorithms course and achieved an A, (iv) Whether they have a job offer fro Google, (v) Whether they have a job offer from Facebook, (vi) The number of misspelled words on their resume. You decide to represent each candidate i T by a corresponding 6-dimensional feature vector f(x(9). You believe that if you just knew the right weight vector w E 6 you could reliably predict the quality of a candidatei by computing w. f(x). To determine uw your boss lets you sample pairs of candidates from the pool. For a pair of candidates (k, l) you can have them face off in a "DataMining-fight." The result is score (k l), which tells you that candidate k is at least score 1) better than candidate I. Note that the score will be negative when I is a better candidate than k. Assume you collected scores for a set of pairs of candidates P Describe how you could use a perceptron based algorithm to learn the weight vector w. Make sure to describe the basic intuition; how the weight updates will be done; and pseudo-code for the entire algorithm

Explanation / Answer

The most recent development in Natural Language Processing (NLP) comes from a start-up called MetaMind, which has developed a language recognition system that is more accurate than the leading systems available on the market.
MetaMind has published new research detailing how their neural networking system uses a kind of artificial short-term memory to answer a wide range of questions about a piece of natural language.

According to MetaMind, the system can answer everything from very specific queries about what the text describes to more general questions like “What’s the sentiment of the text?” or “What’s the French translation?” The research, due to appear next week at Arxiv.org, a popular online repository for academic papers, echoes similar research from Facebook and Google, but it takes this work at step further.

MetaMind was founded by Richard Socher, a prominent machine-learning expert who obtained his PhD from Stanford where he worked with Chris Manning and Andrew Ng. Socher tested his algorithms using a data set compiled by Facebook for measuring machine performance at routine comprehension tasks. MetaMind's software ended up outperforming Facebook's own algorithms.

in1 = tf.placeholder(dtype=tf.float32, shape=[batch_size, input_size])

in2 = tf.placeholder(dtype=tf.float32, shape=[batch_size, input_size])

target = tf.placeholder(dtype=tf.int32, shape=[batch_size,1])

weights = tf.Variable(tf.random_uniform([input_size,1], dtype=tf.float32))

out1 = tf.matmul(in1, weights)

out2 = tf.matmul(in2, weights)

score = out1 - out2

loss = tf.losses.mean_squared_error(target, score)

train_step = tf.train.GradientDescentOptimizer(learning_rate=0.1).minimize(loss)

Related Questions

Navigate

• Browse (All)
• Browse Y
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.