Machine Learning, Deep Learning + AWS Sagemaker

Learn Machine Learning, Deep Learning, Bayesian Learning and Model Deployment with Sagemaker in Python.

4.38 (412 reviews)
Udemy
platform
English
language
Other
category
16,420
students
17.5 hours
content
Jul 2022
last update
$79.99
regular price

What you will learn

Deep Learning with Tensorflow!!!

Deep Learning with PyTorch!!! Yes both Tensorflow + PyTorch!

AWS Sagemaker

Data Analysis with Pandas

Using Scikit-learn to its full effect

Algorithms from scratch using Numpy

Model Deployment

Bayesian learning with PyMC3

Model Diagnostics

Natural Language Processing

Unsupervised Learning

Natual Language Processing with Spacy

Time series modelling with FB Prophet

Python

Description

This is a course on Machine Learning, Deep Learning (Tensorflow + PyTorch) and Bayesian Learning (yes all 3 topics in one place!!!). Yes BOTH Pytorch and Tensorflow for Deep Learning.

We learn how to deploy models in AWS Sagemaker. Along the way we heavily use boto3 to spin up sagemaker instances.

We start off the course by analysing data using pandas, and implementing some algorithms from scratch using Numpy. These algorithms include linear regression, Classification and Regression Trees (CART), Random Forest and Gradient Boosted Trees.

We start off using TensorFlow for our Deep Learning lessons. This will include Feed Forward Networks, Convolutional Neural Nets (CNNs) and Recurrent Neural Nets (RNNs). For the more advanced Deep Learning lessons we use PyTorch with PyTorch Lightning.

We focus on both the programming and the mathematical/ statistical aspect of this course. This is to ensure that you are ready for those theoretical questions at interviews, while being able to put Machine Learning into solid practice.

Some of the other key areas in Machine Learning that we discuss include, unsupervised learning, time series analysis and Natural Language Processing. Scikit-learn is an essential tool that we use throughout the entire course.

We spend quite a bit of time on feature engineering and making sure our models don't overfit. Diagnosing Machine Learning (and Deep Learning) models by splitting into training and testing as well as looking at the correct metric can make a world of difference.

I would like to highlight that we talk about Machine Learning Deployment, since this is a topic that is rarely talked about. The key to being a good data scientist is having a model that doesn't decay in production.

I hope you enjoy this course and please don't hesitate to contact me for further information.

Content

Introduction

Introduction
How to tackle this course
Installations and sign ups
Jupyter Notebooks
Course Material

Basic python

Intro
Basic Data Structures
Dictionaries
Python functions (methods)
Numpy functions
Conditional statements
For loops
Dictionaries again

Pandas

Intro
Pandas simple functions
Subsetting
loc and iloc
loc and iloc 2
map and apply
groupby

Numpy

Gradient Descent
Kmeans part 1
Kmeans part 2
Broadcasting

Scikit-Learn

Intro
Linear Regresson Part 1
Linear Regression Part 2
Classification and Regression Trees
CART part 2
Random Forest theory
Random Forest Code
Gradient Boosted Machines

Plotting

Plotting resources (notebooks)
Line plot
Plot multiple lines
Histograms
Scatter Plots
Subplots
Seaborn + pair plots

Classification

Kaggle part 1
Kaggle part 2
Theory part 1
Theory part 2 + code
Titanic dataset
Sklearn classification prelude
Sklearn classification
Dealing with missing values

Time Series

Intro
Loss functions
FB Prophet part 1
FB Prophet part 2
Theory behind FB Prophet

Model Diagnostics

Overfitting
Cross Validation
Stratified K Fold
Area Under Curve (AUC) Part 1
Area Under Curve (AUC) Part 2

Unsupervised Learning

Principal Component Analysis (PCA) theory
Fashion MNIST PCA
K-means
Other clustering methods
DBSCAN theory
Gaussian Mixture Models (GMM) theory

Natural Language Processing

Intro
Stop words and Term Frequency
Term Frequency - Inverse Document Frequency (Tf - Idf) theory
Financial News Sentiment Classifier
NLTK + Stemming
N-grams
Word (feature) importance

NLP Part 2 (Spacy)

Spacy intro
Feature Extraction with Spacy (using Pandas)
Classification Example
Over-sampling

Regularization

Introduction
MSE recap
L2 Loss / Ridge Regression intro
Ridge regression (L2 penalised regression)
S&P500 data preparation for L1 loss
L1 Penalised Regression (Lasso)
L1/ L2 Penalty theory: why it works

Deep Learning

Intro
DL theory part 1
DL theory part 2
Tensorflow + Keras demo problem 1
Activation functions
First example with Relu
MNIST and Softmax
Deep Learning Input Normalisation
Softmax theory
Batch Norm
Batch Norm Theory

Convolutional Neural Nets

Intro
Fashion MNIST feed forward net for benchmarking
Keras Conv2D layer
Model fitting and discussion of results
Dropout theory and code
MaxPool (and comparison to stride)

Model Deployment

Intro
Saving Models
FastAPI intro
FastAPI serving model

Final Thoughts

Some advice on your journey

Screenshots

Machine Learning, Deep Learning + AWS Sagemaker - Screenshot_01Machine Learning, Deep Learning + AWS Sagemaker - Screenshot_02Machine Learning, Deep Learning + AWS Sagemaker - Screenshot_03Machine Learning, Deep Learning + AWS Sagemaker - Screenshot_04

Reviews

Fred
July 21, 2023
The structure is a bit missing about where you are heading to. You could invent a use case and produce this with pandas...
Varun
July 12, 2023
This course has an incredible mix of breadth and depth - we cover details from NLP to transformers to bayesian programming with pymc3 and all the way to model deployment. This feels almost textbook like as a resource in that I can refer to this course for a whole bevy of topics (definitely check out the Time Series Prophet section) which makes for an incredible resource to have in your pocket.
Mirantha
March 8, 2023
I recently completed this Machine Learning course on Udemy, and I must say it was an exceptional experience! The instructor was knowledgeable and engaging and made complex concepts easy to understand. The course was well-structured and covered a wide range of topics. The hands-on assignments and projects were particularly useful in reinforcing the concepts and allowing me to apply them to real-world scenarios. The instructor provided excellent support, promptly addressing any questions or concerns that arose. Overall, I would highly recommend this course to anyone interested in learning about machine learning!
Patrick
December 1, 2022
This is the best ML course that I have ever seen! Just completed the course (assignments and all) and landed a job offer, thanks to the concepts taught in the course. The concepts are all very clearly explained. The instructor, Sachin, is certainly one of the best instructors in Machine Learning.
Shilpi
August 25, 2022
The tutor has gone above and beyond to make the course content. I am really happy with the content. Knowledge imparted is equivalent to the 9 month course provided by Columbia university diploma course.
Spirit
July 4, 2022
I found this course to be detailed and well explained, building on top of my reading about ML to date.
Jonathan
May 31, 2022
Sachin is great at breaking down complex topics and explaining it step by step in an easily consumable way. Highly recommend!
Giridhar
May 18, 2022
I loved the course Sachin, I understood in depth of some of the concepts, will be helpful if you could add more nlp techniques using transformer for QA, Summarization,Ner and zeroshot and fewshot learning.
Eugene
April 16, 2022
very concise and straight to the point. Hope the deployment section can be beef up further though. maybe at least cover deployment on EC2, or using sagemaker etc..
Nik
April 11, 2022
Absolutely loving this course. Sachin is a great instructor as well as an active engineer with skin in the game. He provides a great mix of theory and practical application here.
Conti
April 6, 2022
I stopped following the lessons, I cannot really understand what author is saying,. Moreover, the explanations themselves are sometimes quite puzzling. Eventually it made me lose my will and my patience
Thomas
March 24, 2022
This is a very good and comprehensive set of lectures that covers a wide range of analytical tools. Not only does it cover worked examples it provides the mathematical background so often missed by many courses. From this you can see that the presenter has a excellent grounding in the field with a deep knowledge of the technology and why you should use them. My background is developing ML for some 35 years, particularly within the field of biology and big-data. I used this course to catch up with current scripting tools as my background is in the core algorithms that underlay the tools.
Sheldon
February 15, 2022
This course introduced fundamental ML concepts and tools in a way that me as a newbie in ML could understand. No doubt one of the best courses for ML out there!
Canh
February 15, 2022
Thank Dr. Sachin for the great course. This course is not too deep mathematical but more practical instead. All contents are well explained with coding examples. Highly recommend it to anyone who would like to start a machine learning journey in a practical way.
Christian
November 15, 2021
I am still working on the course, as I looked into the thing I was more interested to learn first, but I can say that the course is excelent, and I will recommend it. Clear and concise is the word. Also, he is extremely really helpful as well!!!! I will recommend this course.

Coupons

DateDiscountStatus
3/1/202187% OFF
expired
10/19/2021100% OFF
expired
12/21/2021100% OFF
expired

Charts

Price

Machine Learning, Deep Learning + AWS Sagemaker - Price chart

Rating

Machine Learning, Deep Learning + AWS Sagemaker - Ratings chart

Enrollment distribution

Machine Learning, Deep Learning + AWS Sagemaker - Distribution chart
3780696
udemy ID
1/17/2021
course created date
3/1/2021
course indexed date
Bot
course submited by