Google’s Artificial Intelligence – AUTOMATED MACHINE LEARNING (AutoML)

Google has just created an Artificial Intelligence that is capable of creating Al by itself. This GOOGLE’S AUTOML Outperforms any artificial intelligence made by Humans.

What is Automated Machine Learning (AutoML)

It is the work of a team of researchers at Google brain. The researchers at used re-enforced learning to create Al inception as described by Google CEO Sundar Pichai

The goal of AutoML is to make machine learning more accessible by automatically generating a data analysis pipeline that can include data pre-processing, feature selection, and feature engineering methods along with machine learning methods and parameter settings that are optimized for your data.

Here is a quote from Google’s research blog,

“In our approach (which we call ‘AutoML’), a controller neural net can propose a ‘child’ model architecture, which can then be trained and evaluated for quality on a particular task,” the company explains on the Google Research Blog. “That feedback is then used to inform the controller how to improve its proposals for the next round. We repeat this process thousands of times — generating new architectures, testing them, and giving that feedback to the controller to learn from.”



AutoML Work Samples

AutoML is aimed to create programs that can be used out-of-the-box by ML novices. The tech was recently used to accomplish the following tasks.

  • AutoWEKA is an approach for the simultaneous selection of a machine learning algorithm and its hyperparameters; combined with the WEKApackage it automatically yields good models for a wide variety of data sets.
  • Deep neural networks are notoriously dependent on their hyperparameters, and modern optimizers have achieved better results in setting them than humans (Bergstra et alSnoek et al).
  • Making a science of model search: a complex computer vision architecture could automatically be instantiated to yield state-of-the-art results on 3 different tasks: face matching, face identification, and object recognition.

The Google researchers automated the design of machine learning models using an approach called reinforcement learning. Where AutoML acts as a controller neural network that develops a child AI network for a specific task. For this particular child AI, which the researchers called NASNet, the task was recognizing objects — people, cars, traffic lights, handbags, backpacks, etc. — in a video in real-time.

According to the researchers, NASNet was 82.7 percent accurate at predicting images on ImageNet’s validation set. This is 1.2 percent better than any earlier published results, and the system is also 4 percent more efficient, with a 43.1 percent mean Average Precision (mAP). Additionally, a less computationally demanding version of NASNet outperformed the best similarly sized models for mobile platforms by 3.1 percent.

AI has the potential to affect almost all aspects of human lifestyle. It’s already being used to advance in healthcare, finance, agriculture, and so many other fields. Google’s AutoMl remarkable technology that can bring machine-powered advancement in technology, but I sincerely hope, it will lead to better tools helpful to humans, and not a destroyer.

Watch this YouTube video

AI codes its own ‘AI Child’ – Artificial Intelligence breakthrough! – ColdFusion

Sources:

connect with us

subscribe to our newsletter