Introduction to Machine Learning and Deep Learning

PyTorch Basics: Tensors & Gradients

Linear Regression with PyTorch

Working with Image Data in PyTorch

Image Classification using Convolutional Neural Networks

Residual Networks, Data Augmentation and Regularization Techniques

Generative Adverserial Networks

Requirements

Basic Linear Algebra (matrix multiplication)

Basic Python Programming

Basic Calculus (Derivatives)

Description

“Deep Learning with PyTorch for Beginners is a series of courses covering various topics like the basics of Deep Learning, building neural networks with PyTorch, CNNs, RNNs, NLP, GANs, etc. This course is Part 1 of 5.

Topics Covered:

1. Introduction to Machine Learning & Deep Learning 2. Introduction on how to use Jovian platform 3. Introduction to PyTorch: Tensors & Gradients 4. Interoperability with Numpy 5. Linear Regression with PyTorch – System setup – Training data – Linear Regression from scratch – Loss function – Compute gradients – Adjust weights and biases using gradient descent – Train for multiple epochs – Linear Regression using PyTorch built-ins – Dataset and DataLoader – Using nn.Linear – Loss Function – Optimizer – Train the model – Commit and update the notebook 7. Sharing Jupyter notebooks online with Jovian

Who this course is for:

Beginner Python developers curious about Deep Learning and PyTorch

Understand the intuition behind Artificial Neural Networks

Build artificial neural networks with Tensorflow

Classify images, data using deep learning

Apply Convolutional Neural Networks in practice

Requirements

Some prior coding experience with python is required.

Description

Neural networks are a family of machine learning algorithms that are generating a lot of excitement. They are a technique that is inspired by how the neurons in our brains function. They are based on a simple idea: given certain parameters, it is possible to combine them in order to predict a certain result. For example, if you know the number of pixels in an image, there are ways of knowing which number is written in the image. The data that enters passes through various “ layers” in which a series of adjusted learning rules are applied by a weighted function. After passing through the last layer, the results are compared with the “correct” results, and the parameters are adjusted.

Although the algorithms and the learning process in general are complex, one the network has learned, it can freeze the various weights and function in a memory or execution mode. Google uses these types of algorithms, for example, for image searches.

There is no single definition for the meaning of Deep Learning. In general, when we talk of Deep Learning, we are referring to a group of Machine Learning algorithms based on neural networks that, as we have seen, are characterized by cascade data processing. The entrance signal passes through the various stages, and in each one, they are subjected to a non-linear transformation. This helps to extract and transform the variable according to the determined parameters (weights or boundaries). There isn’t an established limit for the number of stages that a neural network must contain to be considered Deep Learning. However, it is thought that Deep Learning arose in the 80’s, using a model which had 5 or 6 layers. It was (and is) called the neocognitron and was created by the Japanese researcher Kunihiki Fukushima. Neural networks are very effective in identifying patterns.

An example worth highlighting of the application of Deep Learning is the project carried out by Google and the Universities of Stanford and Massachusetts. It aimed to improve the natural language processing techniques of a type of AI called Recurrent Neural Network Language Model (RNNLM). It’s used for automatic translations and creating subtitles, among other thing. Basically, it builds up phrases word by words, basing each word on the previous one and in this way, it can even write poems.

Module 1

1. Introduction to Deep Learning and TensorFlow

2. Basics of Neural Networks

3. Designing a shallow neural network (Scratch and python) (Project)

4. Deeper neural network using TensorFlow. (Project)

This is a preview to the exciting Recurrent Neural Networks course that will be going live soon. Recurrent Networks are an exciting type of neural network that deal with data that come in the form of a sequence. Sequences are all around us such as sentences, music, videos, and stock market graphs. And dealing with them requires some type of memory element to remember the history of the sequences, this is where Recurrent Neural networks come in.

We will be covering topics such as RNNs, LSTMs, GRUs, NLP, Seq2Seq, attention networks and much much more.

You will also be building projects, such as a Time series Prediction, music generator, language translation, image captioning, spam detection, action recognition and much more.

Building these projects will impress even the most senior machine learning developers; and will prepare you to start tackling your own deep learning projects with real datasets to show off to your colleagues or even potential employers.

Sequential Networks are very exciting to work with and allow for the creation of very intelligent applications. If you’re interested in taking your machine learning skills to the next level, then this course is for you!

Wanna understand deep learning and neural networks so well, you could code them from scratch? In this course, we’ll do exactly that.

The course starts by motivating and explaining perceptrons, and then gradually works its way toward deriving and coding a multiclass neural network with stochastic gradient descent that can recognize hand-written digits from the famous MNIST dataset.

Course Goals

This course is all about understanding the fundamentals of neural networks. So, it does not discuss TensorFlow, PyTorch, or any other neural network libraries. However, by the end of this course, you should understand neural networks so well that learning TensorFlow and PyTorch should be a breeze!

Challenges

In this course, I present a number of coding challenges inside the video lectures. The general approach is, we’ll discuss an idea and the theory behind it, and then you’re challenged to implement the idea / algorithm in Python. I’ll discuss my solution to every challenge, and my code is readily available on github.

Prerequisites

In this course, we’ll be using Python, NumPy, Pandas, and good bit of calculus. ..but don’t let the math scare you. I explain everything in great detail with examples and visuals.

If you’re rusty on your NumPy or Pandas, check out my free courses Python NumPy For Your Grandma and Python Pandas For Your Grandpa.

Who this course is for:

People interested in learning how neural networks work

Basics of Image Processing for deep learning using tensorflow

Image Classification

Tensorflow

Machine Learning

Deep Learning

Neural Networks

Requirements

Basics of Python 3 programming

Description

Want to dive into Deep Learning and can’t find a simple yet comprehensive course?

Don’t worry you have come to the right place.

We provide easily digestible lessons with plenty of programming question to fill your coding appetite. All topic are thoroughly explained and NO MATH BACKGROUND IS NEEDED. This class will give you a head start among your peers.

This class contains fundamentals of Image Classification with Tensorflow.

This course will teach you everything you need to get started.

Who this course is for:

Data Scientists

If you have some Knowledge about Python and want to explore Deep learning

Beginner python developer curious about Data Science

Undertand the theory of different Sequence Modeling Applications

Requirements

Some Basic High School Mathematics

Some Basic Programming Knowledge

Some basic Knowledge about Neural Networks

Description

In this course, you’ll learn the following:

RNNs and LSTMs

Sequence Modeling

PyTorch

Building a Chatbot in PyTorch

We will first cover the theoretical concepts you need to know for building a Chatbot, which include RNNs, LSTMS and Sequence Models with Attention.

Then we will introduce you to PyTorch, a very powerful and advanced deep learning Library. We will show you how to install it and how to work with it and with PyTorch Tensors.

Then we will build our Chatbot in PyTorch!

Please Note an important thing: If you don’t have prior knowledge on Neural Networks and how they work, you won’t be able to cope well with this course. Please note that this is not a Deep Learning course, it’s an Application of Deep Learning, as the course names implies (Applied Deep Learning: Build a Chatbot). The course level is Intermediate, and not Beginner. So please familiarize yourself with Neural Networks and it’s concepts before taking this course. If you are already familiar, then your ready to start this journey!

Who this course is for:

Anybody enthusiastic about Deep Learning Applications

Are you still wondering what ChatGPT is all about? Why some people are calling it the ‘steam engine’ moment in AI history? Will it change our future in a significant way?

This basic course in ‘Decoding GPT’ may help you answer some of the above questions. You dont need any technical or coding background to know the basic fundamentals covered in the course. This course is designed for functional consultants, product managers as well as developers and architects.

The course covers the basic theory of language and why it is difficult for computers. It covers chronologically the scientific progress made in natural language processing. It explains the pre-GPT era using statistical models and later using neural networks like RNN. The recent development in chat GPT has fundamentally changed this knowledge area.

The course talks about the theory behind transformers and how they can handle the natural language tasks so well. The course also has hands-on sessions on the use of Chat GPT and the GPT APIs to create our own custom applications. In the final section the course talks about the future of GPT and how these tools can eventually lead to the creation of artificial general intelligence.

This course is for beginners and no background in computers or AI is required.

Who this course is for:

Business executives, Software application developers

Simple implementation of convolutional neural networks, deep neural networks, recurrent neural networks, and linear regression

Understanding of keras syntax

Understanding of different deep learning algorithms

Requirements

Basic python knowledge

Familiarity with data science and numpy

Description

When I started learning deep learning, I had a hard time figuring out how everything worked. What library was the best for me? Which algorithms worked best for which data set? How could I know my model was accurate? I spent a lot of time on tutorials, courses and reading to try and answer these questions. In the end, I felt like the process I took to learn deep learning was too inefficient. That is why I created this course.

Learn Keras: Build 4 Deep Learning Applications is a course that I designed to solve the problems my past self had. This course is designed to get you up and running with deep learning as quickly as possible. We use keras in this course because it is one of the easiest libraries to learn for deep learning. Each video, we go over a different machine learning algorithm and its use cases. The four algorithms we focus on the most are:

1. Linear Regression

2. Dense Neural Networks

3. Convolutional Neural Networks

4. Recurrent Neural Networks

In conclusion, if you are looking at a quick intro into deep learning, this course is for you.

So what are you waiting for? Let’s get started!

Who this course is for:

Someone who wants to get into machine learning but feels overwhelmed by other tutorials

Someone who is interested in machine learning but doesn’t know where to start

Machine learning and artificial intelligence hold the potential to transform healthcare and open up a world of incredible promise. But we will never realize the potential of these technologies unless all stakeholders have basic competencies in both healthcare and machine learning concepts and principles.

This course will introduce the fundamental concepts and principles of machine learning as it applies to medicine and healthcare. We will explore machine learning approaches, medical use cases, metrics unique to healthcare, as well as best practices for designing, building, and evaluating machine learning applications in healthcare. The course will empower those with non-engineering backgrounds in healthcare, health policy, pharmaceutical development, as well as data science with the knowledge to critically evaluate and use these technologies. Co-author: Geoffrey Angus Contributing Editors: Mars Huang Jin Long Shannon Crawford Oge Marques The Stanford University School of Medicine is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians. Visit the FAQs below for important information regarding 1) Date of original release and Termination or expiration date; 2) Accreditation and Credit Designation statements; 3) Disclosure of financial relationships for every person in control of activity content.

WHAT YOU WILL LEARN

Define important relationships between the fields of machine learning, biostatistics, and traditional computer programming.

Learn about advanced neural network architectures for tasks ranging from text classification to object detection and segmentation.

Learn important approaches for leveraging data to train, validate, and test machine learning models.

Understand how dynamic medical practice and discontinuous timelines impact clinical machine learning application development and deployment.

Machine Learning, often called Artificial Intelligence or AI, is one of the most exciting areas of technology at the moment. We see daily news stories that herald new breakthroughs in facial recognition technology, self driving cars or computers that can have a conversation just like a real person. Machine Learning technology is set to revolutionise almost any area of human life and work, and so will affect all our lives, and so you are likely to want to find out more about it. Machine Learning has a reputation for being one of the most complex areas of computer science, requiring advanced mathematics and engineering skills to understand it. While it is true that working as a Machine Learning engineer does involve a lot of mathematics and programming, we believe that anyone can understand the basic concepts of Machine Learning, and given the importance of this technology, everyone should. The big AI breakthroughs sound like science fiction, but they come down to a simple idea: the use of data to train statistical algorithms. In this course you will learn to understand the basic idea of machine learning, even if you don’t have any background in math or programming. Not only that, you will get hands on and use user friendly tools developed at Goldsmiths, University of London to actually do a machine learning project: training a computer to recognise images. This course is for a lot of different people. It could be a good first step into a technical career in Machine Learning, after all it is always better to start with the high level concepts before the technical details, but it is also great if your role is non-technical. You might be a manager or other non-technical role in a company that is considering using Machine Learning. You really need to understand this technology, and this course is a great place to get that understanding. Or you might just be following the news reports about AI and interested in finding out more about the hottest new technology of the moment. Whoever you are, we are looking forward to guiding you through you first machine learning project.

NB this course is designed to introduce you to Machine Learning without needing any programming. That means that we don’t cover the programming based machine learning tools like python and TensorFlow.

WHAT YOU WILL LEARN

You will understand the basic of how modern machine learning technologies work

You will be able to explain and predict how data affects the results of machine learning

You will be able to use a non-programming based platform train a machine learning module using a dataset

You will be able to form an informed opinion on the benefits and dangers of machine learning to society