There has been a recent surge in popularity of Deep Learning, achieving state of the art performance in various tasks like Language Translation, playing Strategy Games and Self Driving Cars requiring millions of data points. One common barrier for using deep learning to solve problems is the amount of data needed to train a model. The requirement of large data arises because of the large number of parameters in the model that machines have to learn.
When working on a problem specific to your domain, often the amount of data needed to build models of this size is impossible to find. However models trained on one task capture relations in the data type and can easily be reused for different problems in the same domain. This technique is referred to as Transfer Learning.
Few people ever saw the images of China girls, although for decades they were ubiquitous in movie theaters. At the beginning of a reel of film, there would be a few frames of a woman’s head. She might be dressed up; she might be scowling at the camera. She might blink or move her head.
But if audiences saw her, it was only because there had been a mistake. These frames weren’t for public consumption. The China girl was there to assist the lab technicians processing the film. Even though the same person’s face might show up in reel after reel of film, her image would remain unknown to everyone except the technicians and projectionists.
For many years photo labs would produce unique China girl images; around a couple hundred women, perhaps more, had their images hidden at the beginning of films. As movies have transitioned from analog to digital, though, the China girls are disappearing.
Driving the roads in Mountain View and Sunnyvale is one thing, but in San Fransisco, it is a whole different ball game and a much harder problem to solve. He pointed out that you can expect to encounter cars doing strange maneuvers, pedestrians spilling across the curbs, cyclists weaving in their lanes, etc. So, when we see the streets of San Fransisco conquered, then we know that self-driving is ready to come of age.
The water whispered to Simon’s brain as it passed his lips. It told him of its purity, of mineral levels, of the place it was bottled. The bottle was cool in his hand, chilled perfectly to the temperature his neural implants told it he preferred. Simon closed his eyes and took a long, luxurious swallow, savoring the feel of the liquid passing down his throat, the drops of condensation on his fingers.