Thread
Everything you use today is powered by machine learning🚀.
Even this tweet was recommended to you by an ML algorithm🔥.
But do you know where ML came from?
Here's the story of how ML came into the world 🌎.
--A Thread--
🧵
Even this tweet was recommended to you by an ML algorithm🔥.
But do you know where ML came from?
Here's the story of how ML came into the world 🌎.
--A Thread--
🧵
Machine learning has its roots in the 1940s.
The book "The Organization of Behavior" by Donald Heb, in 1949, proposed theories about how neural networks relate to brain activity.
The Turing Test was created in 1950 to determine if a computer is intelligent.
The book "The Organization of Behavior" by Donald Heb, in 1949, proposed theories about how neural networks relate to brain activity.
The Turing Test was created in 1950 to determine if a computer is intelligent.
In the Turing Test, a computer needs to convince a human being that it's also a human being.
In 1952, Arthur Samuel proposed a computer learning program. He created a program that could play checkers and improve its performance over time.
In 1952, Arthur Samuel proposed a computer learning program. He created a program that could play checkers and improve its performance over time.
In 1957 Frank Rosenblatt built the first neural network for computers, mimicking the working of the human brain.
In 1967, the nearest neighbor algorithm was introduced, enabling computers to perform pattern recognition.
In 1967, the nearest neighbor algorithm was introduced, enabling computers to perform pattern recognition.
In the 1980s and 1990s, backpropagation algorithms were reintroduced, allowing neural networks to learn from complex and unstructured data.
Unfortunately, the models were shallow and had limited learning capabilities.
Unfortunately, the models were shallow and had limited learning capabilities.
Fast forward to 1997, and IBM's Deep Blue beat a human in chess.
Support vector machines and other statistical methods rose in the early 2000s.
In 2006, @geoffreyhinton, coined the name "deep learning", and the rest is history.
Support vector machines and other statistical methods rose in the early 2000s.
In 2006, @geoffreyhinton, coined the name "deep learning", and the rest is history.
Convolutional Neural Networks were introduced in 2009.
In 2012, AlexNet won the ImageNet challenge beating all previous algorithms and setting a new era for computer vision.
In 2014, @goodfellow_ian invented GANs, which revolutionized the image generation space.
In 2012, AlexNet won the ImageNet challenge beating all previous algorithms and setting a new era for computer vision.
In 2014, @goodfellow_ian invented GANs, which revolutionized the image generation space.
In 2016, DeepMind developed AlphaGo, which beat the world champion in the Chinese board game.
In 2017, AlphaGo beat champions in the Go, Chess, and Shogi games.
In 2017, AlphaGo beat champions in the Go, Chess, and Shogi games.
In 2017, @GoogleAI introduced the transformer architecture through their seminal paper Attention Is All You Need.
Transformers have gone ahead to completely change the NLP space, and through Vision Transformers, they have also started eating CNNs pie in CV space.
Transformers have gone ahead to completely change the NLP space, and through Vision Transformers, they have also started eating CNNs pie in CV space.
In 2020, Denoising Diffusion Probabilistic Models were introduced for image generation.
In 2022, @StabilityAI released Stable Diffusion, an image generation model that took the world by storm with its ability to generate high-quality images without requiring massive compute.
In 2022, @StabilityAI released Stable Diffusion, an image generation model that took the world by storm with its ability to generate high-quality images without requiring massive compute.
2022 also saw the introduction of ChatGPT by @OpenAI , garnering millions of users in a matter of weeks.
With ChatGPT-4 expected to be released any time now, it can only get better from here.
With ChatGPT-4 expected to be released any time now, it can only get better from here.
Want to see the complete ML history timeline? Here's a great article by @BernardMarr .
www.forbes.com/sites/bernardmarr/2016/02/19/a-short-history-of-machine-learning-every-manager-should-...
Follow @themwiti for content on machine learning and deep learning.
www.forbes.com/sites/bernardmarr/2016/02/19/a-short-history-of-machine-learning-every-manager-should-...
Follow @themwiti for content on machine learning and deep learning.
Follow @themwiti for more content on machine learning and deep learning.
Mentions
See All
Sumanth @Sumanth_077
·
Mar 13, 2023
Nice thread this Derrick.