Abacus.AI Profile picture
The world's first AI super assistant and general-purpose agent - DeepAgent. We have two products: ChatLLM for professionals and Abacus Enterprise
Aug 11, 2023 10 tweets 2 min read
Backpropagation and Gradient Descent - The dynamic duo of deep learning

Ever wondered about the mathematics behind NN training? Here is a simplified way to understand the process:

1/10 Image 1. Initialize the neural network: Create a neural network and initialize it with random weights and biases.

2. Feedforward pass: NN predicts an outcome based on input. For example: does the input image have a cat?

2/10
Jul 25, 2023 11 tweets 6 min read
Solve more problems.

Solving problems is the best way to learn Machine Learning, but most people don't know where to start.

Here are 10 projects you can use to kick off your journey: 1. Titanic: Machine Learning from Disaster

This is the perfect project to get started with classification algorithms.

It will teach you some feature engineering practices, and you can solve the problem with a simple decision tree.

https://t.co/L8foURs9PYkaggle.com/c/titanic
Image
Jul 24, 2023 9 tweets 4 min read
Here is a FREE guide to learning the Mathematics of AI/ML.

Organized into three sections:

• Probability and Statistics
• Linear Algebra
• Multivariate Calculus

7 resources for all levels.

Let's start: 1. Seeing Theory

An interactive website that takes you through some of the most critical probabilities and statistics concepts.

These should be enough to get you started, and you will have fun going through it! https://t.co/rx4tLQ2c2Mseeing-theory.brown.edu
Image
Jun 18, 2023 8 tweets 4 min read
Free machine learning education.

Many top universities publicly make their Machine Learning and Deep Learning programs available. All of this information is now online and free for everyone!

Here are 6 of these programs.

Pick one and get started! Image Introduction to Deep Learning
MIT Course 6.S191
Alexander Amini and Ava Soleimany

Introductory course on deep learning methods and practical experience using TensorFlow.

Covers applications for computer vision, natural language processing, and more.

introtodeeplearning.com Image
Apr 25, 2023 5 tweets 2 min read
For those who write software:

The more specific you are, the better results you'll get from ChatGPT.

Here are a few techniques to improve your results and a few examples: Phrase your prompts with positive instructions.

Create a session dedicated to working with Python. Initialize it with the following prompt.

Tell ChatGPT what you want to get instead of what you don't want. Image
Apr 20, 2023 6 tweets 1 min read
Building Machine Learning Systems is a team effort.

If you want to build a team, here are the roles you need:

• AI Architect
• Data Scientist
• Data Engineer
• Machine Learning Engineer

Here is the responsibility of each of these roles: AI Architect

This person focuses on the architecture of the overall system.

The architect is the interface between data scientists, data engineers, machine learning engineers, operations, development, UI/UX, and business unit leaders.
Apr 16, 2023 12 tweets 3 min read
Python 🐍 is a world-class language.

Here are some of the features that make it one of the most popular languages in the world:

1/12 You can slice and dice arrays very easily.

2/12 Image
Apr 14, 2023 6 tweets 1 min read
Here are 4 problems we recommend if you want to start with Machine Learning from the basics: Problem 1

The Titanic Challenge in Kaggle is among the most popular problems for beginners.

This is a classification problem that deals with structured data. It will show you the impact of good feature engineering.
Apr 3, 2023 9 tweets 5 min read
Here is a FREE guide to learning the Mathematics of AI/ML.

Organized into three sections:

• Probability and Statistics
• Linear Algebra
• Multivariate Calculus

7 resources for all levels.

Let's start: 1. Seeing Theory

An interactive website seeing-theory.brown.edu that takes you through some of the most critical probabilities and statistics concepts.

These should be enough to get you started, and you will have fun going through it!
Mar 29, 2023 12 tweets 6 min read
Solve more problems.

Solving problems is the best way to learn Machine Learning, but most people don't know where to start.

Here are 10 projects you can use to kick off your journey: 1. Titanic: Machine Learning from Disaster

This is the perfect project to get started with classification algorithms.

It will teach you some feature engineering practices, and you can solve the problem with a simple decision tree.

kaggle.com/c/titanic
Mar 27, 2023 8 tweets 4 min read
Free machine learning education.

Many top universities are publicly making their Machine Learning and Deep Learning programs available. All of this information is now online and free for everyone!

Here are 6 of these programs.

Pick one and get started! Image Introduction to Deep Learning
MIT Course 6.S191
Alexander Amini and Ava Soleimany

Introductory course on deep learning methods and practical experience using TensorFlow.

Covers applications for computer vision, natural language processing, and more.

introtodeeplearning.com Image
Mar 8, 2023 12 tweets 5 min read
10 YouTube videos for anyone starting with machine learning.

On libraries, algorithms, and tools: 1. Notebooks are a fantastic way to code, experiment, and communicate your results.

Take a look at @CoreyMSchafer's fantastic 30-minute tutorial on Jupyter Notebooks.

Feb 24, 2023 12 tweets 2 min read
11 key concepts of machine learning: Target (also referred to as "y")

The target is the piece of information that we are predicting.

For example:

• the animal that's shown in a picture
• the price of a house
• whether a message is spam or not
Feb 3, 2023 12 tweets 5 min read
10 YouTube videos for anyone starting with machine learning.

On libraries, algorithms, and tools: 1. Notebooks are a fantastic way to code, experiment, and communicate your results.

Take a look at @CoreyMSchafer's fantastic 30-minute tutorial on Jupyter Notebooks.

Feb 1, 2023 6 tweets 3 min read
One of the most useful Python libraries that you can learn is Pandas.

Especially if you want to build some skills in the data engineering or machine learning space, Pandas is crucial.

Here is what you need to know to get started right away. ↓ Pandas is an open-source library to analyze and manipulate data.

Some people even consider it the most powerful library to deal with data in any language!
Jan 23, 2023 12 tweets 6 min read
Solving problems is the best way to learn Machine Learning.

But most people don't know where to start.

Here are 10 projects you can use to kick off your journey: 1. Titanic: Machine Learning from Disaster

This is the perfect project to get started with classification algorithms.

It will teach you some feature engineering practices, and you can solve the problem with a simple decision tree.

kaggle.com/c/titanic