Goto

Collaborating Authors

automl


Big Tech & Their Favourite Deep Learning Techniques

#artificialintelligence

Interestingly, they all seem to have picked a particular school of thought in deep learning. With time, this pattern is becoming more and more clear. For instance, Facebook AI Research (FAIR) has been championing self-supervised learning (SSL) for quite some time, alongside releasing relevant papers and tech related to computer vision, image, text, video, and audio understanding. Even though many companies and research institutions seem to have their hands on every possible area within deep learning, a clear pattern is emerging. But, of course, all of them have their favourites. In this article, we will explore some of the recent work in their respective niche/popularised areas.


Fast AutoML with FLAML + Ray Tune - KDnuggets

#artificialintelligence

FLAML is a lightweight Python library from Microsoft Research that finds accurate machine learning models in an efficient and economical way using cutting edge algorithms designed to be resource-efficient and easily parallelizable. FLAML can also utilize Ray Tune for distributed hyperparameter tuning to scale up these AutoML methods across a cluster. AutoML is known to be a resource and time consuming operation as it involves trials and errors to find a hyperparameter configuration with good performance. Since the space of possible configuration values is often very large, there is a need for an economical AutoML method that can more effectively search them. To address both of these factors, Microsoft Researchers have developed FLAML (Fast Lightweight AutoML).


What Does the Future of Machine Learning Look Like?

#artificialintelligence

Machine learning solutions continue to incorporate changes into businesses' core processes and are becoming more prevalent in our daily lives. The global machine learning market is predicted to grow from $8.43 billion in 2019 to $117.19 billion by 2027. Despite being a trending topic, the term'machine learning' is often used interchangeably with the concept of artificial intelligence. In fact, machine learning is a subfield of artificial intelligence based on algorithms that can learn from data and make decisions with minimal or no human intervention. Many companies have already begun using machine learning algorithms due to their potential to make more accurate predictions and business decisions. In 2020, $3.1 billion in funding was raised for machine learning companies.


Fast AutoML with FLAML + Ray Tune

#artificialintelligence

FLAML is a lightweight Python library from Microsoft Research that finds accurate machine learning models in an efficient and economical way using cutting edge algorithms designed to be resource-efficient and easily parallelizable. FLAML can also utilize Ray Tune for distributed hyperparameter tuning to scale up these AutoML methods across a cluster. AutoML is known to be a resource and time consuming operation as it involves trials and errors to find a hyperparameter configuration with good performance. Since the space of possible configuration values is often very large, there is a need for an economical AutoML method that can more effectively search them. To address both of these factors, Microsoft Researchers have developed FLAML (Fast Lightweight AutoML).


AutoML with FLAML & Python: Machine Learning in 15 Seconds

#artificialintelligence

The other cool thing about this library is the use of frugal optimization for cost-related hyperparameters. In essence, algorithms can have hyperparameters which can cause a large variation in the training cost. Most of the hyperparameter optimization techniques don't take this into consideration, meaning they are searching for the best results without taking costs as a viable benchmark. This technique is largely based on the randomized direct-search method, and you can learn more about it in the following paper. FLAML library significantly outperforms top-ranked AutoML libraries on large open-source AutoML benchmarks.


Do we need AutoML… or AutoDM (Automated Data Management)?

#artificialintelligence

I suggest that you check out the chat stream. The comments were very enlightening. My takeaway is that the concept of AutoML is good, but scope of the AutoML vision is missing 80% of the AI/ML model development and operationalization – providing high quality and complete data that feeds the AI/ML models. Figure 5 from "Big Data to Good Data: Andrew Ng Urges ML Community to Be More Data..." nicely summarizes the broader AutoML challenge with respect to data management.


The Machine Learning Schools Championed by the Biggest AI Labs in the World

#artificialintelligence

I recently started an AI-focused educational newsletter, that already has over 80,000 subscribers. TheSequence is a no-BS (meaning no hype, no news etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Recently, one of my students asked me a question as of whether DeepMind was solely working in reinforcement learning applications. The answer is obviously no but the question is still valid as it rooted in the fact that most of DeepMind's highly publicized work such as AlphaGo, MuZero or AlphaFold are based in reinforcement learning.


Emerging technologies in Data Science

#artificialintelligence

Technologies are masters, ruling the world of Data! As of now, we all know that without Network and Data the entire globe will be stuck and drown in the huge economic crisis. The connectivity around the world through networks is successfully established by the Data. Every matter is considered to be data either physically or virtually. The tremendous amount of data that are generating every second by most of the citizens of the world.


Practical Data Science

#artificialintelligence

In the first course of the Practical Data Science Specialization, you will learn foundational concepts for exploratory data analysis (EDA), automated machine learning (AutoML), and text classification algorithms. With Amazon SageMaker Clarify and Amazon SageMaker Data Wrangler, you will analyze a dataset for statistical bias, transform the dataset into machine-readable features, and select the most important features to train a multi-class text classifier. You will then perform automated machine learning (AutoML) to automatically train, tune, and deploy the best text-classification algorithm for the given dataset using Amazon SageMaker Autopilot. Next, you will work with Amazon SageMaker BlazingText, a highly optimized and scalable implementation of the popular FastText algorithm, to train a text classifier with very little code. Practical data science is geared towards handling massive datasets that do not fit in your local hardware and could originate from multiple sources.


Get out of the "Which Model?" mental block

#artificialintelligence

You are in your final year of undergraduate, and your final-year capstone presentation is due in like, 5 days? Desperately you pick up that Kaggle Dataset, (sent to you by your friend to perhaps? I don't know.), to get out that pretty looking 90% Accuracy. But you're essentially stuck at step 0, which model to use? Trust me, I have been there. Immediately you start googling "How to Select Machine Learning Model", and you are faced with terms like Interpretability, Bias, Variance, Data Format, Linearity, and whatnot.