The next Stage of Machine Learning: Teach Robots to Think Like Humans
We're teaching robots to learn in all kinds of new ways.
The human brain is a never-ending source of wonder. In recent years, scientists and engineers have made major progress in figuring out how to replicate key facets of human thinking in machines, thus contributing to a better understanding of the mind. But despite years of research, many processes remain a mystery... at least for now.
A recent experiment from MIT demonstrates the capabilities of machine learning. Researchers have figured out how to make a machine identify certain classes of objects (in this case, handwritten characters) after only having seen a couple examples. By giving the computer information about how the characters were created, the machine was then able to understand the components that make up writing and replicate them itself.
But what about machines being able to identify abstract objects? How do humans always recognize a cup as a cup, regardless of what color, shape, size, or texture it is? And how can we do so even when we only see a portion of the object?
A new study from Georgia Tech researchers displays progress in the creation of machines that can replicate human thinking with regard to “random projection,” as it’s called. The researchers realized that humans use less than 1 percent of the data available about an object to identify it. They believe that their findings explain how humans are able to process all kinds of visual data so quickly in navigating the world on any average day.
The key to the machine's ability to copy humans in this regard is the extent to which researchers have programmed it to replicate the neural networks that humans have. As another example, researchers at UC Berkeley have been using neural network programming to build a robot that can teach itself to walk, just as a toddler would over time.
We’ve clearly come a long way since the early days of computers and robotics. With all the breakthroughs we’ve seen so far, one can’t help but wonder just how smart robots can get?
Image Credit: pogonici via Shutterstock
Stefani is a writer and urban planner based in Oakland, CA. She holds a master’s in City and Regional Planning from UC Berkeley and a bachelor’s in Human Biology from Stanford University. In her free time, she is often found reading diverse literature, writing stories, or enjoying the outdoors. Follow her on Twitter:@stefanicox
In a breakthrough for nuclear fusion research, scientists at China's Experimental Advanced Superconducting Tokamak (EAST) reactor have produced temperatures necessary for nuclear fusion on Earth.
- The EAST reactor was able to heat hydrogen to temperatures exceeding 100 million degrees Celsius.
- Nuclear fusion could someday provide the planet with a virtually limitless supply of clean energy.
- Still, scientists have many other obstacles to pass before fusion technology becomes a viable energy source.
Military recruits are supposed to be assessed to see whether they're fit for service. What happens when they're not?
- During the Vietnam War, Robert McNamara began a program called Project 100,000.
- The program brought over 300,000 men to Vietnam who failed to meet minimum criteria for military service, both physically and mentally.
- Project 100,000 recruits were killed in disproportionate numbers and fared worse after their military service than their civilian peers, making the program one of the biggest—and possibly cruelest—mistakes of the Vietnam War.
The 116th Congress is set to break records in term of diversity among its lawmakers, though those changes are coming almost entirely from Democrats.
- Women and nonwhite candidates made record gains in the 2018 midterms.
- In total, almost half of the newly elected Congressional representatives are not white men.
- Those changes come almost entirely from Democrats; Republican members-elect are all white men except for one woman.
SMARTER FASTER trademarks owned by The Big Think, Inc. All rights reserved.