Deep learning has been the most popular subset of machine learning in recent times. Deep learning can probably perform numerous tasks which have uses in medical science, city administration, computer science, gaming and the list goes on.
We’ll talk about the recent technologies which took the Deep Learning community’s attention.
That sounds cool! What’s Deep Learning? No Math, please.
Deep learning is a subset or sub-field of machine learning. Machine learning is itself a subset of Artificial Intelligence.
Trending AI Articles:
1. Making a Simple Neural Network
2. From Perceptron to Deep Neural Nets
3. Neural networks for solving differential equations
4. Turn your Raspberry Pi into homemade Google Home
It’s basically machine learning which takes place with the help Artificial Neural Networks which are deep, meaning they have one or more hidden layers.
Back to the topic.
1) Waymo Self Driving Cars
Self-driving cars are the future of the motor industry. These cars can navigate through streets and manage passenger workload.
- Deep learning is used in mechanisms which detect road alignment. If the road is developing a curve of suppose 30 degrees, then the steering wheel should also rotate to some extent to make the car turn.
- Also, infrared sensors continuously emit radiations which cover a specific region around the car. If any object comes in this region, the car tracks its proximity and stops accordingly.
Also, Tesla is planning to release a Robotic Car in the market by 2020.
2) Google Duplex
It immediately gained popularity as soon as it was demonstrated in the Google I/O 2018. It is a major achievement in Natural language Processing which is a branch of AI.
It can make hotel reservations, book tables, make appointments with Google Assistant. The machine actually makes a call to the vendor and makes a meaningful conversation with him/her.
- Google Duplex was trained on phonic conversations collected from various sources. It used Recurrent Neural Networks to produce an output statement given a question and the state of the conversion.
3) Developing a piece of art-Making Portraits
This painting went into an auction for millions of dollars. It was produced using a GAN ( Generative Adversarial Network ). These networks could produce music, pictures and also modify them in a real-looking style.
- GAN has a generator network which produces a random image from a noise vector.
- The discriminator network distinguishes between the real image and the image produced by the generator. The generator improves itself from the loss it receives from the discriminator.
Hope you find the article interesting. For any queries and suggestions, feel free to express them in the comments below. Thank You.