3 Times Machine Learning gave me the goosebumps!

My kid loves a storybook by the name of “The Gruffalo…” A mouse walking through a jungle meets a series of predators. He escapes each and every one of them by making up stories of a non-existent creature called a “Gruffalo” and scares them away. There is a twist though – creature is for real!! The mouse manages to pretend his way and get out of the pickle – the little brat outsmarts his own creation 😅

I wonder sometimes if AI / ML is like a Gruffalo! Frankly most of the hype around it seems make-belief. The biggest disservice to the field of machine learning is actually this word called AI. It promotes fear that AI will trounce humans or will one day take over the world. We at least today seem to be far from such a dystopian scenario. Almost all science community agrees that we are far away from achieving AGI or Artifical general intelligence or what is also popularly referred to as the ‘singularity’.

Let us extend the Gruffalo metaphor a bit – while most agree about the wrongness of fear mongering on AI, we should be open to precaution. Perhaps the creature is not make belief after all! Very recently I have come across 3 things that have given me the creeps when it comes to what machine learning can become!!

1. Reinforcement learning agents learn how to use tools and form strategies without additional programming

Elon Musk’s Open AI just released a paper in which they describe a simulated training environment in which they make agents (RIL) play a game of hide and seek. The environment progressively introduces 6 strategies and counterstrategies. What they observed was incredible, they observed emergent complex tool usage. As an example, hiding agents using boxes to block doors so that they cannot be discovered by seeker agents. Seeking agents using ramps to jump over obstacles, hiders using ramps and hiding them in rooms to prevent them from being used for jumping over by seekers. If this type of “completely unprogrammed” behaviour is not intelligence then I don’t know what is! Please read a blog post by OpenAI here.

2. Google Duplex RNNs enable a natural sounding calling service for restaurant bookings etc was out of this world – borderline spooky as well.

https://youtu.be/ijwHj2HaOT0

This is the first time synthetic speech was indistinguishable from human speech. To use it, improvise it and do it at Google scale was simply an incredible feat for speech synthesis, natural language understanding and processing and apparently a factory of human agents as well 😄 jokes aside this really gave me goose bumps. Google uses RNNs for this. See conceptual architecture and the link to original Google blog here.

3. Breakthrough language model GPT 2 released recently by OpenAI achieves state of the art performance on many language processing benchmarks and performs rudimentary machine translation, comprehension and summaries

I don’t think people appreciate how much of a big deal this is. Basically you feed the model some seed and it generates many many paragraphs of coherent human like text on its own, replete with stories, meaning and full sense. If you read it you will not believe that an AI wrote it. I have previously written about how tech / social is being misused. You add this and you have a frankenstein-ish monster on your hands. This can be used to generate fake news en masse and it would be really hard to detect. It can be used to impersonate people, for identity theft and many more. On a positive side it will make bots, writing assistants translation, and knowledge systems remarkably useful and human like! For an AI that is the ultimate goal. See an example below from openAI original blog post.

The scientist named the population, after their distinctive horn, Ovid’s Unicorn. These four-horned, silver-white unicorns were previously unknown to science.

Now, after almost two centuries, the mystery of what sparked this odd phenomenon is finally solved.

Dr. Jorge Pérez, an evolutionary biologist from the University of La Paz, and several companions, were exploring the Andes Mountains when they found a small valley, with no other animals or humans. Pérez noticed that the valley had what appeared to be a natural fountain, surrounded by two peaks of rock and silver snow.

While it is impossible to list down many incredible feats achieved in this path breaking tech, I wanted to cite a few examples that gave me the goose bumps. Perhaps if you are interested you should also check out DeepFakes and MuseNet and do share in comments what did you find exciting.

I believe we are looking at building blocks of higher intelligence getting better and better, you could say we are helping machines evolve faster in their own right – but most still believe we are far away from AGI, or singularity… But are we?

Ps. This blog post was written by a human, and if you don’t believe it, ask Gruffalo 😅