Written by Charmaine Lai (Numenta Marketing Associate) and Niels Leadholm

Image for post
Image for post

If you’ve watched our research meetings for the past few weeks, you may see a fresh face or hear a new voice on our videos. That is the face and voice of a PhD student Niels Leadholm, who spent 12 weeks with Numenta as a visiting research scholar. As one of Numenta’s first “virtual” interns, I asked Niels to share his work and experience interning at Numenta.

Q1: Hi Niels, can you tell us a bit about yourself and your area of research and expertise?

Sure! I’m a PhD student at the Oxford Lab for Theoretical Neuroscience and Artificial Intelligence . My interest is in understanding primate vision at a computational level, and using this understanding to improve artificial systems. Our lab looks at what is known about how our brains process visual information at both a high level (think psychology) and a low level (think neuroscience), and how this could inform improvements to machine learning approaches. My original background was actually as a medical doctor, but my passion for AI led me down online courses in mathematics and machine learning, and here I am today! One of my main focuses is on why engineered systems are vulnerable to what are known as adversarial examples — these are images that have been altered by small amounts of targeted noise (often so little that it’s imperceptible to a human), but a machine vision system becomes confident that the new image is something totally different. It’s hard to explain because it’s so counterintuitive to our own notion of recognising an object — you look at these and think, how could a system that is capable of classifying difficult images of tea cups and chihuahuas possibly think a school bus is an ostrich? …


Written by Charmaine Lai, Numenta Marketing Associate

Image for post
Image for post

AlphaGo, a computer Go program developed by Google DeepMind, might have beaten 18-time world champion Lee Sedol at a Go match, but Lee used a mere 20 Watts to operate, less power than a lightbulb. In contrast, AlphaGo used 1,920 CPUs and 280 GPUs, which is 50,000 times as much power as what Lee’s brain uses.

Deep learning networks are hitting bottlenecks when they scale to more complex tasks and bigger models. Many of these models require enormous amounts of power, raising sustainability issues and creating environmental threats. …


Written by Lucas Souza, Numenta Research Staff Member

Image for post
Image for post

About a year ago, in the post The Case for Sparsity in Neural Networks, Part 1: Pruning , we discussed the advent of sparse neural networks, and the paradigm shift that signals models can also learn by exploring the space of possible topologies in a sparse neural network. We showed that combining gradient descent training with an optimal sparse topology can lead to state of the art results with smaller networks. …


Written by Vicenzo Lomanco, Numenta Visiting Research Scientist

Image for post
Image for post

My name is Vincenzo Lomonaco and I’m a Postdoctoral Researcher at the University of Bologna where, in early 2019, I obtained my PhD in computer science working on “ Continual Learning with Deep Architectures “ in the effort of making current AI systems more autonomous and adaptive. Personally, I’ve always been fascinated and intrigued by the research insights coming out of the 15+ years of Numenta research at the intersection of biological and machine intelligence. …


Written by Lucas Souza, Numenta Research Staff Member

Image for post
Image for post

Last week at Numenta we held our monthly Brains@Bay meetup, gathering data scientists and researchers in the Bay Area to talk about Sparsity in the brain and in Neural Networks (recordings available here). Sparsity is a topic we’ve also been extensively discussing in our research meetings and journal clubs in the past weeks.

Sparsity has long been a foundational principal of our neuroscience research, as it is one of the key observations about the neocortex: everywhere you look in the brain, the activity of neurons is always sparse. Now as we work on applying our neuroscience theories to machine learning systems, sparsity remains a key focus. There are so many different aspects to it, so let’s start at the beginning. …


Written by Jeff Hawkins, Co-founder and Christy Maver, VP of Marketing

First posted in March 2018; updated in January 2019

In our most recent peer-reviewed paper, A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex, we put forward a novel theory for how the neocortex works. The Thousand Brains Theory of Intelligence proposes that rather than learning one model of an object (or concept), the brain builds many models of each object. Each model is built using different inputs, whether from slightly different parts of the sensor (such as different fingers on your hand) or from different sensors altogether (eyes vs. skin). The models vote together to reach a consensus on what they are sensing, and the consensus vote is what we perceive. …


Written by Donna Dubinsky, CEO and Christy Maver, VP of Marketing

Image for post
Image for post

Last month, Numenta released a major new theory for intelligence and cortical computation. As we do with all of our research, the team documented the theory in a research paper and made it available on a preprint server while kicking off the submission process with a peer-reviewed journal. However, we also did something we’ve never done before: we (Donna and Christy) created a “companion piece” to the research paper. What’s a companion piece and why did we write it? How did two non-neuroscientists write a paper about a neuroscience paper? …


Written by Subutai Ahmad, VP of Research

Image for post
Image for post

As some of you know, we recently posted a major new paper titled “A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex”. We were very fortunate to receive coverage in the New York Times. The article was written about Jeff, our team, and the unusual nature of the research being done at Numenta. Cade Metz, the reporter, did a great job of summarizing, for the layman, the science behind the theoretical framework. The scientific material can be hard to understand, so I appreciated the clear description.

However, the article left some scientists with the impression that we were a closed door research lab, isolated from the rest of the scientific world. While it is true that Numenta is different, the notion that we are secretive and detached could not be further from the truth. …


Written by Christy Maver, VP of Marketing

Image for post
Image for post

Intelletic Trading Systems (ITS) (www.intelletic.com) is the developer of a purely quantitative, proprietary artificial intelligence (AI) based platform making us a market leader in autonomous trading of futures and other assets. Our platform is designed to generate greater profit and incur less risk than any human discretionary trader.

The company came out of my experience as a trader and my belief that AI will be a disruptive technology in many fields, but especially in financial services. It’s only common sense that a machine can process vast amounts of data faster and more consistently than a human. …


Written by Scott Purdy, Research Staff Member

Image for post
Image for post

What’s Old is New Again: The Evolutionary Context of the Neocortex

Our primary research interest at Numenta is the neocortex in mammals. We are on a mission to understand how the neocortex works, in order to understand intelligence in the brain. While we often talk about the essential principles of the neocortex, we don’t talk much about how it came to be.

The neocortex evolved and rapidly expanded in a very short amount of time (on evolutionary scales, at least). Yet it has an incredibly complex structure. So much so, that an understanding of the functionality of the full circuit eludes researchers to this day. …

About

Numenta

Where Neuroscience Meets Machine Intelligence

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store