Home Courses Applied Machine Learning Online Course Testing and Debugging ML/AI systems end to end

Testing and Debugging ML/AI systems end to end

Instructor: Applied AI Course

This content is restricted. Please Login

Prev
Next
Live session on Time Series Analysis and Forecasting
Interview Questions on Productionization, Deployment
1.1
Introduction
15 min
1.2
Moving window for Time Series Data
15 min
1.3
Fourier decomposition
22 min
1.4
Deep learning features: LSTM
8 min
1.5
Image histogram
15 min
1.6
Keypoints: SIFT.
10 min
1.7
Deep learning features: CNN
4 min
1.8
Relational data
10 min
1.9
Graph data
12 min
1.10
Indicator variables
7 min
1.11
Feature binning
14 min
1.12
Interaction variables
9 min
1.13
Mathematical transforms
4 min
1.14
Model specific featurizations
9 min
1.15
Feature orthogonality
12 min
1.16
Domain specific featurizations
4 min
1.17
Feature slicing
10 min
1.18
Kaggle Winners solutions
7 min
2.1
Calibration of Models:Need for calibration
8 min
2.2
Calibration Plots.
17 min
2.3
Platt’s Calibration/Scaling.
8 min
2.4
Isotonic Regression
11 min
2.5
Code Samples
5 min
2.6
Modeling in the presence of outliers: RANSAC
13 min
2.7
Retraining models periodically.
8 min
2.8
A/B testing.
22 min
2.9
VC dimension
22 min
2.10
Data Science Life cycle
17 min
2.11
Productionization and deployment of Machine Learning Models
17 min
2.12
Productionization and deployment + Spark
96 min
2.13
Hands on Live Session: Deploy an ML model using Flask APIs on AWS
125 min
2.14
Building web apps for ML/AI using StreamLit
101 min
2.15
Building web apps for ML/AI using StreamLit - II
66 min
2.16
ML Model productionization using Heroku
120 min
2.17
Amazon Sagemaker--Part 1
147 min
2.18
Amazon sagemaker--part 2
161 min
2.19
SageMaker Part 3: Distributed training and Deep Learning
127 min
2.20
SageMaker Part 4: Spark and Pipelines
121 min
2.21
Amazon SageMaker : Part 5 [Miscellaneous topics]
97 min
2.22
Design and Productionization of low latency ML systems
93 min