Summary of “Brain-Computer Interfaces Show That Neural Networks Learn by Recycling”

The hallmark of intelligence is the ability to learn.
The brain may be highly flexible and adaptive overall, but at least over short time frames, it learns by inefficiently recycling tricks from its neural repertoire rather than rewiring from scratch.
Now, while observing activity in the brain during learning, Yu and his colleagues have seen evidence of a similar lack of plasticity at the neural level.
In 2014, the researchers observed that test subjects could learn new tasks more easily if they involved patterns of neural activity within the intrinsic manifold rather than outside it.
Then the team switched the neural activity requirements for moving the cursor and waited to see what new patterns of neural activity, corresponding to new points in the intrinsic manifold, the animals would use to accomplish them.
Why would the brain use less than the best strategy for learning? The group’s findings suggest that, just as the neural architecture constrains activity to the intrinsic manifold, some further constraint limits how the neurons reorganize their activity during the experiments.
Chase likened the motor cortex to an old-fashioned telephone switchboard, with neural connections like cables linking inputs from other cortical areas to outputs in the brain’s cerebellum.
The researchers can’t yet rule out the possibility that reassociation is a fast interim way for the brain to learn new tasks; over a longer time period, realignment or rescaling might still show up.

The orginal article.

Summary of “Foreign languages: How to memorise vocabulary”

When trying to learn a foreign language, most of us have the same complaint: “I’m just not good at memorising.” Learning new vocabulary can be daunting, especially for busy adults whose minds are already occupied with work, family, and other responsibilities.
A comfort? Linguists say that to “Get by” in a language, such as directing a taxi or asking for a phone number, it takes a vocabulary of about 120 basic words.
Forget the long vocabulary study sheets, or reading the dictionary.
Experts say that learners are capable or retaining 10-20 words per study hour.
If you do 15 minutes of self-study per day, set a weekly vocabulary goal of 20-25 words and phrases.
That’s only six weeks until the 120-word “Survival kit” is learned and memorised.
Those one-word-a-day language learning apps may feel convenient, but thematically, they’re all over the place, delivering a chain of unrelated words: envelope, tired, January, receive, onion.
The mind naturally clusters connected words together, so learning, say, types of weather in one lesson, and parts of the body the next, works in tune with your brain’s natural system for classifying information.

The orginal article.

Summary of “Research: Learning a Little About Something Makes Us Overconfident”

The students thought they were much further along in the learning curve toward workplace success than their future employers did.
Specifically, our research focused on the common task of probabilistic learning in which people learn to read cues from the environment to predict some outcome.
Participants estimated their accuracy rate was 73% when it had not hit even 60%. It appears that Alexander Pope was right when he said that a little learning is a dangerous thing.
In our studies, just a little learning was enough to make participants feel they had learned the task.
Other research has found that doctors learning to do spinal surgery usually do not begin to make mistakes until their 15th iteration of the surgery.
As with probabilistic learning, it has been shown that most people under the age of 18 have little knowledge of personal finance.
Personal finance is something most learn by trial and error.
Of course, the beginner must struggle to learn – but the beginner must also guard against an illusion they have learned too quickly.

The orginal article.

Summary of “A Little-Known Hack to Learn a New Skill in a Fraction of the Time”

Deliberate practice refers to the intensely focused practice of a skill, habit, or ability.
To practice deliberately, you have to break down skills into blocks of discrete micro-skills, map out the order in which you need to learn those micro-skills, and closely monitor your progress.
For some skills, it can be easy to find proven curricula to guide your deliberate practice.
Ask yourself, “Where do I anticipate having an opportunity in the course of my actual day-to-day business life, to practice this skill?” Maybe you can practice this new micro-skill during a conversation with an employee, a meeting with your management team, or a phone call with a vendor.
Then consider what it would look like for you to start practicing this new micro-skill.
Namely, what were two, three, or four things that you did well? And what was one specific lesson that you learned from this practice session-something that you’d like to handle differently next time?
If you practice it every day for three or four days a week, you’ll find that you can acquire new skills with incredible rapidity.
These are the five elements that transform “Practice” into “Deliberate practice.” Good luck using them to speed up your development of your staff.

The orginal article.

Summary of “If you want to stay successful, learn to think like Leonardo da Vinci”

I’ve been fortunate and done relatively well for myself in the time I’ve been active, and yet I don’t read marketing books, and nor do I spend all that much time trying to formally learn about it.
Reality is redundant, and when you learn widely, that becomes clearer and clearer.
A higher rate of learning You learn how to learn by continuously challenging yourself to grasp concepts of a broad variety.
Learning itself is a skill, and when you exercise that skill across domains, you get specialized as a learner in a way that someone who goes deep doesn’t.
You learn how to learn by continuously challenging yourself to grasp concepts of a broad variety.
It explains how some of history’s polymaths were able to contribute in such a specialized way even though they were primarily focused on going broad. Now, in a world where narrow Artificial Intelligence systems are going to displace most routine, specialized work, it isn’t too much of stretch to assume that this skill of learning to learn across disciplines may just be the difference between those who reinvent themselves and those who don’t.
The takeaway “Develop your senses-especially learn how to see. Realize that everything connects to everything else.”
“Study the science of art. Study the art of science. Develop your senses-especially learn how to see. Realize that everything connects to everything else.”

The orginal article.

Summary of “Your next computer could improve with age”

Google researchers have published details of a project that could let a laptop or smartphone learn to do things better and faster over time.
Litz believes it should be possible to apply machine learning to every part of a computer, from the low-level operating system to the software that users interact with.
Moore’s Law is finally slowing down, and the fundamental design of computer chips hasn’t changed much in recent years.
Tim Kraska, an associate professor at MIT who is also exploring how machine learning can make computers work better, says the approach could be useful for high-level algorithms, too.
A database might automatically learn how to handle financial data as opposed to social-network data, for instance.
“Machine learning makes it possible that the system is automatically customized, to its core, to the specific data and access patterns of a user.”
Kraska cautions that using machine learning remains computationally expensive, so computer systems won’t change overnight.
“The grand vision is a system that is constantly monitoring itself and learning,” he says.

The orginal article.

Summary of “The forgetting curve explains why humans struggle to memorize”

Learning has an evolutionary purpose: Among species, individuals that adapt to their environments will succeed.
The kinds of things humans want to learn are rarely focused on survival; we also use our adaptive, evolutionary memory to remember new languages, 11-step face-washing routines, obscure vocabulary words, and facts about Star Wars.
The forgetting curve is a mathematical formula that describes the rate at which something is forgotten after it is initially learned.
This phenomenon of learning and promptly forgetting information will be familiar to anyone who has tried to cram the night before an exam.
Ebbinghaus made a second discovery: The downward slope of the forgetting curve can be softened by repeating the learned information at particular intervals.
A brain “Stores” memories like files on a hard drive, and software uses “Neural networks” to learn like the human mind does.
The computer won’t forget where the file is, and the neural network can only learn what it’s told to.
Luckily, understanding how the curve works makes it easier to learn things that may not be necessary for survival, but are deeply rewarding.

The orginal article.

Summary of “How to learn a language: Use “spaced repetition””

You memorized how to say essential words and phrases like “Hello,” “Where is the bathroom,” and “I’ll have a beer.” But once you arrived, it’s like your brain had never encountered the language at all.
It’s not you, it’s how you used the flashcards: Learning a language as an adult takes time and effort, but the go-to study methods that most diligent language-learners use are out of date by about hundred years.
Then you will review that word again after a period of time, based on how good your memory of it was.
Studies have shown that, even in animals, spaced repetition works better than trying to learn large batches of information at once.
Five words a day is not as good as 10, but you can still learn a lot at that rate.
The more you can think of the stuff on the flashcard as being part of real life, the easier it will be to learn, and the reason for learning it will be clearer.
SRS is a tool for reinforcing the things that you know are important for your language learning, like words you come across often or grammatical structures that seem useful.
It is no replacement for talking to people in the language you want to learn, writing practice, or reading words in the context of a story or article.

The orginal article.

Summary of “Want to learn statistics? These are the best books, and they’re free to download”

The stats most people learn in high school or college come from the time when computations were done with pen and paper.
People who have taken intro statistics courses might recognize terms like “Normal distribution,” “t-distribution,” and “Least squares regression.” We learn about them, in large part, because these were convenient things to calculate with the tools available in the early 20th century.
We shouldn’t be learning this stuff anymore-or, at least, it shouldn’t be the first thing we learn.
As a former data scientist, there is no question I get asked more than, “What is the best way to learn statistics?” I always give the same answer: Read An Introduction to Statistical Learning.
If you finish that and want more, read The Elements of Statistical Learning.
Statistical learning is meant to take the best ideas from machine learning and computer science, and explain how they can be used and interpreted through a statistician’s lens.
“While knowledge of those topics is very valuable, we believe that they are not required in order to develop a solid conceptual understanding of how statistical learning methods work, and how they should be applied,” says Daniela Witten, a coauthor of An Introduction to Statistical Learning.
The statistical learning tools are wonderful in themselves, but I’ve found they work best for people who are motivated by a personal or professional project.

The orginal article.

Summary of “The GANfather: The man who’s given machines the gift of imagination”

The goal of GANs is to give machines something akin to an imagination.
When future historians of technology look back, they’re likely to see GANs as a big step toward creating machines with a human-like consciousness.
Yann LeCun, Facebook’s chief AI scientist, has called GANs “The coolest idea in deep learning in the last 20 years.” Another AI luminary, Andrew Ng, the former chief scientist of China’s Baidu, says GANs represent “a significant and fundamental advance” that’s inspired a growing global community of researchers.
In one widely publicized example last year, researchers at Nvidia, a chip company heavily invested in AI, trained a GAN to generate pictures of imaginary celebrities by studying real ones.
Once it’s been trained on a lot of dog photos, a GAN can generate a convincing fake image of a dog that has, say, a different pattern of spots; but it can’t conceive of an entirely new animal.
Researchers at Yale University and Lawrence Berkeley National Laboratory have developed a GAN that, after training on existing simulation data, learns to generate pretty accurate predictions of how a particular particle will behave, and does it much faster.
Hany Farid, who studies digital forensics at Dartmouth College, is working on better ways to spot fake videos, such as detecting slight changes in the color of faces caused by inhaling and exhaling that GANs find hard to mimic precisely.
Researchers are already highlighting the risk of “Black box” attacks, in which GANs are used to figure out the machine-learning models with which plenty of security programs spot malware.

The orginal article.