Viraj Tank

Sociomantic Labs

@viraj49

Viraj Tank

@viraj49

AI / ML

HISTORY

1950

Alan Turing creates the “Turing Test” to determine if a computer has real intelligence. To pass the test, a computer must be able to fool a human into believing it is also human.

1952

Arthur Samuel wrote the first computer learning program. The program was the game of checkers, and the IBM computer improved at the game the more it played, studying which moves made up winning strategies and incorporating those moves into its program.

1957

Frank Rosenblatt designed the first neural network for computers (the perceptron), which simulate the thought processes of the human brain.

'67, '79, '81, '85, '90, '97, '06

Numerous scientists and engineers worked hard.

  // This Magical Library Solves My PROBLEM.
  import magicalLibrary

Torch

Caffe

Theano

OpenCV

Paddle

Gluon

Keras

DyNet

2015

Tensorflow was introduced.

  // Tensorflow solves my PROBLEM.
  import tensorflow as tf

1. Gathering Data

2. Preparing Data

3. Selecting Model

4. Training

Model

5. Evaluation

Model

Remaining 20% Data

6. Parameter Tuning

7. Prediction

a) O = x1 + x2 + x3

b) O = (x1 * x2) + x3

Design Algorithm

Design Algorithm

Data

  int arr[3][3][3]=   
        {
            {
            {11, 12, 13},
            {14, 15, 16},
            {17, 18, 19}
            },
            {
            {21, 22, 23},
            {24, 25, 26},
            {27, 28, 29}
            },
            {
            {31, 32, 33},
            {34, 35, 36},
            {37, 38, 39}
            },
        };

Algorithm

• Content Based Recommendation (CBR)

• Collaborative filtering (CF)

• ETC

• Decision making for machines

• ML/AI History

• 7 Steps in Deep Learning

• Designing Recommendation Engine

www.tensorflow.org

Theano

TensorFlow

www.playground.tensorflow.org

Clients

Web

Mobile

TensorFlowLite

  // Load the model from disk.
  TensorFlowInferenceInterface inferenceInterface =
  new TensorFlowInferenceInterface(assetManager, modelFilename);

  // Copy the input data into TensorFlow.
  inferenceInterface.feed(inputName, floatValues, 1, inputSize, inputSize, 3);

  // Run the inference call.
  inferenceInterface.run(outputNames, logStats);

  // Copy the output Tensor back into the output array.
  inferenceInterface.fetch(outputName, outputs);

Android Demo Time

Summary

• AI History

• Deep learning steps

• Recommendation engine

• Tensorflow basics

• Good for ML experiments

• Good for Mobile clients

Thanks