In recent years big companies like Google, Facebook, and Microsoft acquired start-ups (and/or hired talent) that deal with a special branch of Artificial Intelligence (or simply AI) known as Deep Learning. AI is nothing new, and the dream of intelligent machines that can learn and reason have been around well before the 1950’s when the term AI was first coined. In ancient times there were myths about super beings in the form of machines and hybrids that permeated cult imagery and stories with common themes. At the root of these themes is an exploration of human fears and ethical concerns at the spectre of AI. This naturally made its way to Hollywood as early as the original movie Frankenstein, capturing an attempt by humans to forge something more unnatural and artificial.
From “I, Robot” to AMC’s “Humans”
Yesterday I watched the third episode of “Humans”, a new AMC series set in present day London, England which explores AI in the form of human like bots, known as “Synths”, that help with chores around the house, some even provide other more sinister services. In the series, the Synths are capable of highly intelligent conversation, and behaviour, to the point where it’s hard to distinguish them from a real human, except for their glassy green eyes. While this series is a work of fiction, maybe it is not so far fetched from a non-fictional future if the field of AI, esp. as it relates to Deep Learning continues to develop and make progress at the rate it has been.
What is Deep Learning any ways? In the field of AI there is a special branch known as Machine Learning, which traditionally use rule based methods for algorithms that learn from sample data. Another method which has been reinvigorated through recent ground breaking discoveries is now collectively known as Deep Learning. At the heart of this method is an architecture that is loosely based on how the human brain is structured, namely a network of neurons connected by synapses that get excited under certain conditions. This structure is simply known as Neural Network (NN), and it is composed of an input and output layer, with a number of layers in between, known as “hidden” layers. It is said that the first NN was invented in 1958, by a psychologist Frank Rosenblatt, and he called it a Perceptron. It was intended to model how the human brain processed visual data and recognized objects.
So why all the Hype now?
It has something to do with the way these NNs are trained. Each of these neurons has a weight which acts as a knob to reduce or amplify the input signals of the previous layer, and forward it to the next layer for processing. The concept of training comes down to adjusting these weights, which can be thought of as knobs, based on desired outputs given a set of known inputs. So let’s say I feed some NN a picture of a dog as input, and it outputs that it recognizes it as a cat, I would adjust the weights in such a way as to penalize those neurons that gave rise to the output of a cat. This process is known as back-propagation.
Yes yes, but why all the hype now? Well, the general intuition of “having more hidden layers between the inputs and outputs, make for a more intelligent NN” was not realized since there was no feasible method employed that produced better predictions given deeper hidden layers. This all changed in 2006, when Geoffery Hinton, an AI professor and researcher at the University of Toronto made a breakthrough in the way these NNs are trained. Instead of training through back-propagation across all hidden layers, it was more effective to back-propagate one layer at a time, i.e. keep previous layers constant, with a final sweep across all layers for fine tuning. Of course this explanation is overly simplified, and details are beyond the scope of this article. This gave rise to deeper NNs since it was now possible to demonstrate an intelligent gain when more hidden layers were added. Thus Deep Learning was born.
The latest Bot
Unlike the bots (or Synths) in the series Humans, we are nowhere near human like conversations, but a recent attempt by Google, published here looks somewhat promising. The chat bot mentioned in the paper can hold a conversation about the meaning of life, and can even trouble shoot a help desk scenario… well not really! In this case the training set was not a set of pictures of dogs and cats, rather it was a collection of subtitles from movies or transcripts of help desk scenarios. The idea for the subtitles set is to train the NN how to predict the next sentence given the previous sentence. In the subtitles case it is assumed that the 62M sentences are turn based, where one says ABC in one sentence, and the next is a response XYZ, of course this is not always the case, so the data set is said to be “noisy”. Never the less, the idea is to train the NN given input ABC output XYZ. The limitations are obvious, as noted by the authors but it has produced some surprising conversations:
Human: is sky blue or black ?
Machine: blue .
Human: does a cat have a tail ?
Machine: yes .
Human: does a cat have a wing ?
Human: can a cat fly ?
Machine: no .
Human: how many legs does a cat have ?
Machine: four , i think .
Keep in mind that the machine had no prior formal knowledge representation, of cats or the colour of the sky, nor did it use traditional information extraction and rule based query answering crafted by linguists . It simply learned to predict answers given open domain movie subtitles. Looks impressive right? I’d say yes!
The idea of artificial intelligence and the associated fears / ethical concerns have existed since ancient times. The recent methods of Deep Learning are bringing us closer to Hollywood fiction. Does the above “really” represent an intelligent conversation? or is it a surprising outcome of replaying some sentences that simply aligned well with the input? If the machine consistently produced well aligned sentences as answers can that be considered as intelligence? (Turing Test Alert). I tend to think it’s a step closer to realizing the dream of intelligent machines, and it’s something definitely noteworthy, but we’re still a long way off from the Synths portrayed in the Humans series.