[TBD]Learning artificial intelligence

What is AI?

• AI is simulation of human like intelligence in machine

• AI teaches machine and machine becomes smart

• Industrial revolution overcame limitation in muscle power, AI revolution will overcome limitation in human mind power.

• AI is like electricity. Every company is going to use it.

  • AI is the tool for maximising a certain objective function.

  • AI is a very important tool for surveillance capitalism

• Human and machine decision making processes are highly tightly coupled. These interaction is going to increase further in future via AI

  • You are letting GPS to decide the direction

  • You ask mobile APP to decide about best shop

Reference: https://youtu.be/UwsrzCVZAb8

https://youtu.be/5dZ_lvDgevk?t=2042

Affective AI

• A human being is a data in his own

  • How is your teeth

  • How your face looks like

  • By posting pictures in instagram, you are posting your hologram. This can be used by AI to mimic you

Reference: https://youtu.be/UwsrzCVZAb8

Deep learning

Deep learning uses artificial neural networks, which consist of multiple layers of algorithms. Each layer looks at the incoming data, performs its own specialized analysis, and produces an output that other layers can understand. This output is then passed to the next layer, where a different algorithm does its own analysis, and so on.

Types

Feedforward neural network

In a feedforward network, information moves in only one direction from input layer to output layer.

Recurrent neural network

Recurrent neural networks are a widely used artificial neural network. These networks save the output of a layer and feed it back to the input layer to help predict the layer's outcome. Recurrent neural networks have great learning abilities.

They're widely used for complex tasks such as time series forecasting, learning handwriting and recognizing language.

Convolutional neural networks

The neurons in one layer connect not to all the neurons in the next layer, but only to a small region of the layer's neurons. The final output is reduced to a single vector of probability scores, organized along the depth dimension.

Convolutional neural networks have been used in areas such as video recognition, image recognition, and recommender systems.

LSTM(long short-term memory )

Skipthought Vectors

Deep learning vs machine learning

Named-entity recognition

Steps

• Object detection

  • image classification

  • image localization

• Image caption generation

  • Usually, image captioning applications use convolutional neural networks to identify objects in an image and then use a recurrent neural network to turn the labels into consistent sentences.

Language language processing

Use-cases

• • Respond to customer

    • Email

  • Feedback processing

Entities

• • Sentiment

    • It provides the writers behaviour

    • Positive, neutral, negative

  • Intention

    • It provides summary in 1-2 words

Resources

E-book on deep learning

http://neuralnetworksanddeeplearning.com/chap1.html

Listing of important links

https://www.cse.iitk.ac.in/users/sigml/lec/DeepLearningLib.pdf

https://docs.microsoft.com/en-us/azure/architecture/data-guide/big-data/ai-overview?wt.mc_id=AID3018161_QSG_451995&ocid=AID3018161_QSG_451995?utm_source=KonfHub&utm_medium=Social&utm_campaign=add-aionazure

Youtube video on Gradient descent

https://www.youtube.com/embed/IHZwWFHWa-w

Conferences

https://aidevday.konfhub.com/#learningresources

MLBR

https://mlblr.com

References

https://docs.microsoft.com/en-us/azure/machine-learning/concept-deep-learning-vs-machine-learning

https://aischool.microsoft.com/en-us/machine-learning/learning-paths/pix2story-lab/pix2story-introduction/pix2story-overview