Ever wondered how you get relatable & customized feeds on Instagram? How does Instagram achieve this feature? How Google translates an entire web page to a different language?Well, all of this is a product of deep learning
What is Deep Learning(DL)?
DL can be considered as a subset of machine learning (ML) which is a subset of artificial intelligence (AI). It’s a field that is based on learning & improving on its own by examining computer algorithms.
So what is ML & AI ? AI is a technique to enable a machine to mimic human behavior, whereas ML is a technique to achieve AI through algorithms trained on data.
How does DL work?
ANN consists of layers of nodes, much like the human brain is made up of neurons. Nodes within a layer are connected to adjacent layers.
The network is said to be deeper based on the no. of layers it has. Single neuron in the human brain receives thousands of signals from other neurons.
In ANN, signals travel between nodes & assign corresponding weights, heavier weighted nodes will exert more effect on the next layer of nodes.
The final layer compiles the weighted inputs to produce an output.
Let us see an example:
Let’s say, the goal is to have ANN recognize photos of Dogs. So, a training set of images must be compiled, including many e.g. of dog faces at different angles labeled as “dog,” and other pictures that aren’t dogs, labeled “not dog”. Images, fed into the neural network, are converted into data. These data move through the network, and various nodes assign weights to different elements. The final layer compiles the information – furry, has a snout, four legs, etc. – & outputs: “dog”.
Besides this, digital assistants like Siri, Cortana & Alexa use DL for natural language processing and speech recognition.
Skype translates spoken conversations in real-time.
If you know other interesting domains where DL has helped achieve some interesting feats, then do comment below.