Words matter. These are the best Neural Quotes from famous people such as Sebastian Seung, Geoffrey Hinton, Paul Bloom, Robin Marantz Henig, David Chalmers, and they’re great for sharing with your friends.
The neural code usually refers to how your current thoughts and feelings and perceptions are encoded in the signals that neurons are passing around – and it’s not the same. The code is not the same for every person.
I had a stormy graduate career, where every week we would have a shouting match. I kept doing deals where I would say, ‘Okay, let me do neural nets for another six months, and I will prove to you they work.’ At the end of the six months, I would say, ‘Yeah, but I am almost there. Give me another six months.’
Some scholars argue that although the brain might contain neural subsystems, or modules, specialized for tasks like recognizing faces and understanding language, it also contains a part that constitutes a person, a self: the chief executive of all the subsystems.
We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how to get things to work. We just think you can have these great big neural nets that learn, and so, instead of programming, you are just going to get them to learn everything.
Lies can be verbal or nonverbal, kindhearted or self-serving, devious or bald-faced; they can be lies of omission or lies of commission; they can be lies that undermine national security or lies that make a child feel better. And each type might involve a unique neural pathway.
Once your computer is pretending to be a neural net, you get it to be able to do a particular task by just showing it a whole lot of examples.
Actually, I think my view is compatible with much of the work going on now in neuroscience and psychology, where people are studying the relationship of consciousness to neural and cognitive processes without really trying to reduce it to those processes.
Our brains have been designed to blur the line between self and other. It is an ancient neural circuitry that marks every mammal, from mouse to elephant.
When I’m writing, my neural pathways get blocked. I can’t read. I can barely hold a conversation without forgetting words and names. I wish I could wear the same clothes and eat the same food each day.
I think the brain is essentially a computer and consciousness is like a computer program. It will cease to run when the computer is turned off. Theoretically, it could be re-created on a neural network, but that would be very difficult, as it would require all one’s memories.
The paradigm for intelligence was logical reasoning, and the idea of what an internal representation would look like was it would be some kind of symbolic structure. That has completely changed with these big neural nets.
Whatever you are studying right now, if you are not getting up to speed on deep learning, neural networks, etc., you lose. We are going through the process where software will automate software, automation will automate automation.
Each of you possesses the most powerful, dangerous and subversive trait that natural selection has ever devised. It’s a piece of neural audio technology for rewiring other people’s minds. I’m talking about your language.
Just like the brain consists of billions of highly connected neurons, a basic operating unit in a neural network is a neuron-like node. It takes input from other nodes and sends output to others.
Practicing is not only playing your instrument, either by yourself or rehearsing with others – it also includes imagining yourself practicing. Your brain forms the same neural connections and muscle memory whether you are imagining the task or actually doing it.
Both depression and anxiety disorders, for example, are repeatedly described in the media as ‘chemical imbalances in the brain,’ as if spontaneous neural events with no relation to anything outside a person’s brain cause depression and anxiety.
Having been trained as a computer scientist in the ’90s, everybody knew that AI didn’t work. People tried it. They tried neural nets, and none of it worked.
It turns out you can train a neural network on a big body of text. It can be Wikipedia; it can be all the works of Charles Dickens; it could be all of the Internet. They can use grammar and put words together in interesting and convincing ways – and, I think, unexpected and beautiful ways.
A single neuron in the brain is an incredibly complex machine that even today we don’t understand. A single ‘neuron’ in a neural network is an incredibly simple mathematical function that captures a minuscule fraction of the complexity of a biological neuron.
I think the first wave of deep learning progress was mainly big companies with a ton of data training very large neural networks, right? So if you want to build a speech recognition system, train it on 100,000 hours of data.
Now that neural nets work, industry and government have started calling neural nets AI. And the people in AI who spent all their life mocking neural nets and saying they’d never do anything are now happy to call them AI and try and get some of the money.
All you need is lots and lots of data and lots of information about what the right answer is, and you’ll be able to train a big neural net to do what you want.
There are neural networks that can build whole apps from scratch – so why are we teaching high school kids to code?
One can, in principle, outline sort of a set of neural circuits that are critically involved and even identify disorders that affect different components of that neural circuit and see what happens if you knock out, for example, inability to recognize faces, how it affects your response to portraiture.
My main interest is in trying to find radically different kinds of neural nets.
