Deep-learning caught the eyes of the world when Google AI was able to defeat hum player in the ancient game of Go. the game of Go has been the focus of research for AI experts for many years
This brought fame to AI as computer defeated the human for first time in this complex game with umpteenth possibilities.
Previously machines were able to outperform humans in games like – Scrabble, Chess, Othello, and Jeopardy. But Go has been too complex for around a couple of millennia for the computer to defeat
Deep learning has made this possible.
Deep-learning: what is it?
Practically, deep-learning a class of machine learning. Technically it is machine learning where it can learn from a series of data. but there are difference which I will try to clarify below
In case of machine learning, the model learns from some data and then predicts based on it. Overtime with more data it can get better at prediction. but if the predictions goes in wrong direction. the algorithm still needs guidance from humans to adjust the model and then match the results. Whereas, with deep learning, the algorithm can check the outcome using its neural network and apply any tweaks where necessary for accuracy in tasks e.g speech recognition, identifying an object, and language translation.
are Artificial Intelligence, Deep Learning & Machine Learning buzz words for same thing?
Artificial intelligence, deep learning, and machine learning are often used interchangeably
Here’s one liner definitions to make you understand better
- Artificial Intelligence simply means getting your computer to emulate human like behavior in thinking
- Machine learning is a a branch of AI, where data is fed to the computer to learn and derive conclusions from it.
- Deep-learning is a branch of machine learning, which helps in solving more complex problems which we are even not capable of explaining yet.
Understanding the latest advancements in AI can be overwhelming, but if you follow simple logic, you will be able to navigate the landscape
According to Ray Kurtzweil, an American inventor and a futurist predicted stating AI singularity to happen by 2045.
AS HE DEFINES, “THE MOMENT WHEN A 1000$ COMPUTER MAY CONTAIN AS MUCH COMPUTING POWER AS 1000X THE HUMAN BRAIN HAS.”
In short, perhaps we still lack finding the best mathematical formulas. Therefore, till then for learning to properly take place using deep learning, one needs to first feed a large amount of data to the deep learning algorithms.
The Why’s and the How’s
Why does deep learning matters?
Deep learning is capable of deriving accuracy at higher level faster which makes it ideal candidate for areas like safety is self driving cars. Recent developments are making it surpass even humans in some tasks such as safety and image identification
Though deep learning was first defined in the 80s, what took it so long to be a reality
- Large quantities of already labeled data , e.g for prediction of machine failure, it needed the data for thousands of hours of operations clearly marking the failures.
- Big data requires big processing power. Thanks to GPU processing that allows multi core parallel processing reducing the time to process this data and deriving meaning full conclusions from it in real time.
How does it work?
Nearly all of the deep learning methods requires the use of Artificial Neural Network as base
“Deep” means the number of hidden layers in the neural network. Even so, a deep network may contain more than 150 layers whereas a traditional network can have only 2 to 3 hidden layers.
Now, these neural networks composed of layers of nodes, in the same manner as the human brain consisting of neurons. The nodes within the individual layer are connected to adjacent layers. The network is considered deeper based on the number of layers they possess. In a human brain, a single neuron can receive thousands of signals from other neurons. Following the same pattern, signals that have traveled between nodes and have assigned corresponding weights in an artificial neural network, it is said that the heavier the weight of the node is the more effective it will have on the next layer of the node.
So, the last layer compiles all the weighted inputs to produce an output. Since deep learning uses large volumes of data that need further processing that involves severe mathematical calculations. They would require powerful hardware.
When huge data sets are fed in the deep learning system, with the help of artificial neural network this data can be classified with the answers received from the series of binary true or false questions. For instance, a facial recognition functions when it has learned to detect and recognize the lines in the face. Then the more significant part followed by the overall representation of the face.
Applications of deep learning
AI is getting smart day by day and why not. With the amount of computational power, it possesses, machines have the capability of recognizing objects and translating them in real-time. Let us look at the top deep learning applications widely used today.
- Voice search and voice-activated assistants
- Self-driving or driverless cars
- Automatic machine translation
- Automatically adding sound to silent movies
- Automatic handwriting generation
- Automatic text generation
- Image recognition
- Predicting earthquakes
- Automatic colorization
- Neural networks in finance
- Neural networks for detecting brain cancer
- Automatic image caption generation