Artificial Intelligence (ARS)

Build the Most Powerful AI

Hadelin de Ponteves, Kirill Eremenko, SuperDataScience Team, and Ligency Team

Two months ago we discovered that a very new kind of AI was invented.

The kind of AI which is based on a genius idea and that you can build from scratch and without the need for any framework.

We checked that out, we built it, and... the results are absolutely insane.

This game-changing AI called Augmented Random Search, ARS for short.

And in a very simple implementation, it is able to do an exact same thing that Google Deep Mind did in their accomplishment last year - which is to train an AI to walk and run across a field.

However, ARS is 100x times faster and 100x times more powerful.

What's inside

Learning objectives

Build an ai
Understand the theory behind augmented random search algorithm
Learn how to build most powerful ai algorithm

Train and implement ars algorithm
Train ai to solve same challenges as google deep mind

Build an ai
Understand the theory behind augmented random search algorithm
Learn how to build most powerful ai algorithm
Train and implement ars algorithm
Train ai to solve same challenges as google deep mind

Syllabus

Where to get materials

Introduction

Learning Paths

This PDF resource will help you a lot!

Save this course

Save Artificial Intelligence (ARS): Build the Most Powerful AI to your list so you can find it easily later:

Save

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Artificial Intelligence (ARS): Build the Most Powerful AI with these activities:

Review Linear Algebra Fundamentals

Show steps

Solidify your understanding of linear algebra concepts, which are crucial for understanding the mathematical foundations of Augmented Random Search and how it manipulates data.

Browse courses on Linear Algebra

Show steps

Review vector and matrix operations.
Practice solving systems of linear equations.
Understand eigenvalues and eigenvectors.

Brush Up on Calculus Concepts

Show steps

Revisit calculus principles, especially derivatives and gradients, as these are fundamental to understanding how ARS optimizes rewards through methods like finite differences.

Browse courses on Calculus

Show steps

Review differentiation rules.
Practice finding gradients of functions.
Understand optimization techniques.

Discuss ARS Intuition with Peers

Show steps

Engage in discussions with fellow learners to clarify your understanding of the ARS algorithm's intuition and address any conceptual challenges you encounter.

Show steps

Form a study group with other students.
Discuss the ARS algorithm's steps and purpose.
Explain the concepts to each other.

Four other activities

Expand to see all activities and additional details

Show all seven activities

Follow Tutorials on Perceptron Implementation

Show steps

Deepen your understanding of perceptrons, a key component in ARS, by following online tutorials that guide you through the process of implementing them from scratch.

Show steps

Find tutorials on perceptron implementation.
Follow the tutorial step-by-step.
Experiment with different parameters.

Read 'Deep Learning' by Goodfellow et al.

Show steps

Expand your knowledge of deep learning by reading 'Deep Learning' by Goodfellow et al., gaining a broader perspective on the field and understanding how ARS fits within the larger context of AI.

View Deep Learning on Amazon

Show steps

Obtain a copy of the book.
Read relevant chapters on deep learning fundamentals.
Relate the concepts to ARS.

Implement ARS on a Simple Environment

Show steps

Apply your knowledge by implementing the ARS algorithm on a simplified environment, such as a basic game or simulation, to solidify your understanding of its practical application.

Show steps

Choose a simple environment for testing.
Implement the ARS algorithm.
Test and refine your implementation.

Document Your ARS Implementation Journey

Show steps

Create a blog post, video, or presentation documenting your experience implementing the ARS algorithm, sharing insights, challenges, and lessons learned with the broader AI community.

Show steps

Document your implementation process.
Share your insights and challenges.
Publish your documentation online.

Career center

Learners who complete Artificial Intelligence (ARS): Build the Most Powerful AI will develop knowledge and skills that may be useful to these careers:

Reading list

We've selected one books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Artificial Intelligence (ARS): Build the Most Powerful AI.

Deep Learning

Save

Provides a comprehensive introduction to deep learning techniques, which are relevant to understanding the broader context of AI algorithms like Augmented Random Search (ARS). It covers fundamental concepts, mathematical foundations, and practical implementations of various deep learning models. While ARS might be simpler than some deep learning approaches, understanding the landscape of deep learning helps appreciate the strengths and weaknesses of ARS. This book is often used as a textbook in university courses.

Deep Learning

Paperback

$$$

Deep Learning (Adaptive Computation and Machine...

Hardcover

$$$

Deep Learning (Adaptive Computation and Machine...

Kindle Edition

$$$