#GoogleNext17 #Extended #GDGGandhinagar #Codelab 

Agenda ● What is machine learning? ● How does neural networks works? ● Proof: Machine learning is not rocket science!!!! ● Introduction to Google Cloud Platform ● Introduction to Google Cloud Shell ● Detect Objects, Faces, and Landmarks in Images with the Cloud Vision API ● Proficient Entity and Sentiment Analysis with the Natural Language API ● Speech to Text Transcription with the Cloud Speech API ● Your Choice! 

What is machine learning? 

Apple and Orange Example 

Without ML def detect_colors(image): # lots of code def detect_edges(image): # lots of code def analyze_shapes(image): # lots of code def guess_texture(image): # lots of code def define_fruit(image): # lots of code def handle_probability(image): # lots of code 

Solution is Build Classifiers with ML (supervised learning) 

Supervised Learning Recipe Collect Training Data Train Classifier Make Predictions 

1. Linear Regression 2. Logistic Regression 3. Decision Tree 4. SVM 5. Naive Bayes 6. KNN 7. K-Means 8. Random Forest 9. Dimensionality Reduction Algorithms 10. Gradient Boost & Adaboost Tons of machine learning algorithms 

Can these algorithms scale? 

● To understand Neural Networks you need to understand good Math ● To run Neural Networks at scale you need costly GPUs ● To Train Neural Net you need to have lot of training data ● And Perfect model requires lot of reiteration Neural Networks: the scalable solution 

I want something quick!!! What should I do? 

Google Cloud Shell 

Detect Objects, Faces, and Landmarks in Images with the Cloud Vision API 

Proficient Entity and Sentiment Analysis with the Natural Language API 

Speech to Text Transcription with the Cloud Speech API 

Your Choice! 

Q/A 

Thanks