Machine Learning Fundamentals

MLconf 2017 Seattle Lunch Talk - Using Optimal Learning to tune Deep Learning...

In this talk we introduce Bayesian Optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time-consuming or expensive. Deep learning pipelines are notoriously expensive to train and often have many tunable parameters including hyperparameters, the architecture, feature transformations that can have a large impact on the efficacy of the model. We will motivate the problem by giving several example applications using multiple open source deep learning frameworks and open datasets. We’ll compare the results of Bayesian Optimization to standard techniques like grid search, random search, and expert tuning.

Plotcon 2016 Visualization Talk by Alexandra Johnson

Machine learning is full of ideas that are far abstracted away from the underlying data and difficult to understand. Luckily, this represents an amazing opportunity for visualization! These slides dive into the machine learning meta-problem of hyperparameter optimization. We'll show 4 opportunities for visualization in helping people understand, implement, and evaluate hyperparameter optimization strategies.

MLConf 2016 SigOpt Talk by Scott Clark

Using Bayesian Optimization to Tune Machine Learning Models

Scott Clark

Using SigOpt to Tune Deep Learning Models with Nervana Cloud

Using Optimal Learning to Tune Deep Learning Pipelines

Scott Clark

SigOpt talk from NVIDIA GTC 2017 and AWS Popup Loft AI Day We'll introduce Bayesian optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time consuming or expensive. Deep learning pipelines are notoriously expensive to train and often have many tunable parameters, including hyperparameters, the architecture, and feature transformations, that can have a large impact on the efficacy of the model. We'll provide several example applications using multiple open source deep learning frameworks and open datasets. We'll compare the results of Bayesian optimization to standard techniques like grid search, random search, and expert tuning. Additionally, we'll present a robust benchmark suite for comparing these methods in general.

Originally given at MLConf NYC 2017. All large machine learning pipelines have tunable parameters, commonly referred to as hyperparameters. Hyperparameter optimization is the process by which we find the values for these parameters that cause our system to perform the best. SigOpt provides a Bayesian optimization platform that is commonly used for hyperparameter optimization, and I’m going to share some of the common problems we’ve seen when integrating into machine learning pipelines.

Machine learning with scikitlearn

Pratap Dangeti

Automated Machine Learning (Auto ML)

Hayim Makabee

C3 w1

Deep Dive into Hyperparameter Tuning

Shubhmay Potdar

Winning Kaggle 101: Introduction to Stacking

Ted Xiao

Week 4 advanced labeling, augmentation and data preprocessing

Automatic machine learning (AutoML) 101

QuantUniversity

"Automated machine learning (AutoML) is the process of automating the end-to-end process of applying machine learning to real-world problems. In a typical machine learning application, practitioners must apply the appropriate data pre-processing, feature engineering, feature extraction, and feature selection methods that make the dataset amenable for machine learning. Following those preprocessing steps, practitioners must then perform algorithm selection and hyperparameter optimization to maximize the predictive performance of their final machine learning model. As many of these steps are often beyond the abilities of non-experts, AutoML was proposed as an artificial intelligence-based solution to the ever-growing challenge of applying machine learning. Automating the end-to-end process of applying machine learning offers the advantages of producing simpler solutions, faster creation of those solutions, and models that often outperform models that were designed by hand." In this talk we will discuss how QuSandbox and the Model Analytics Studio can be used in the selection of machine learning models. We will also illustrate AutoML frameworks through demos and examples and show you how to get started

Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...

Sri Ambati

Abstract: Explainability in the age of the EU GDPR is becoming an increasingly pertinent consideration for Machine Learning. At QuantumBlack, we address the traditional Accuracy vs. Interpretability trade-off, by leveraging modern XAI techniques such as LIME and SHAP, to enable individualised explanations without necessary limiting the utility and performance of the otherwise ‘black-box’ models. The talk focuses on Shapley additive explanations (Lundberg et al. 2017) that integrate Shapley values from the Game Theory for consistent and locally accurate explanations; provides illustrative examples and touches upon the wider XAI theory. Bio: Dr Torgyn Shaikhina is a Data Scientist at QuantumBlack, STEM Ambassador, and the founder of the Next Generation Programmers outreach initiative. Her background is in decision support systems for Healthcare and Biomedical Engineering with a focus on Machine Learning with limited information.

LinkedIn talk at Netflix ML Platform meetup Sep 2019

Faisal Siddiqi

Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016

MLconf

Building a Machine Learning Platform at Quora: Each month, over 100 million people use Quora to share and grow their knowledge. Machine learning has played a critical role in enabling us to grow to this scale, with applications ranging from understanding content quality to identifying users’ interests and expertise. By investing in a reusable, extensible machine learning platform, our small team of ML engineers has been able to productionize dozens of different models and algorithms that power many features across Quora. In this talk, I’ll discuss the core ideas behind our ML platform, as well as some of the specific systems, tools, and abstractions that have enabled us to scale our approach to machine learning.

Automated Machine Learning

safa cimenli

Machine Learning for .NET Developers - ADC21

C3 w2

Feature Engineering

Kaggle presentation

Mining model for hotel recommendations (Kaggle Challenge)

Arjun Varma

Kaggle Higgs Boson Machine Learning Challenge

Bernard Ong

AWS Forcecast: DeepAR Predictor Time-series

PolarSeven Pty Ltd

Accelerate Machine Learning with Ease using Amazon SageMaker

Organizations are using machine learning (ML) to address a host of business challenges, from product recommendations to demand forecasting. Until recently, developing these ML models took much time and effort, and it required expertise. In this session, we introduce Amazon SageMaker, a fully managed ML service that enables developers and data scientists to develop and deploy deep learning models quickly and easily. We walk through the features and benefits of Amazon SageMaker and discuss the uniquely designed ML algorithms that allow for optimized model training, getting you to production fast.

Build Your Recommendation Engine on AWS Today!

AWS Germany

Recommender systems are an important mechanism to personalize and enhance customer experience. In Amazon, we have been researching recommender systems for over two decades and nowadays AWS customers can use the same technologies to develop, train and deploy their own recommenders systems in just a couple of hours. In my presentation, I will give an overview of the most recent recommender systems papers and techniques, and demonstrate how to train and deploy a recommendation system on AWS in less than 15 minutes.

What's hot

Bayesian Global Optimization

Common Problems in Hyperparameter Optimization

Machine learning with scikitlearn

Pratap Dangeti

Automated Machine Learning (Auto ML)

Hayim Makabee

C3 w1

Deep Dive into Hyperparameter Tuning

Shubhmay Potdar

Winning Kaggle 101: Introduction to Stacking

Ted Xiao

Week 4 advanced labeling, augmentation and data preprocessing

Automatic machine learning (AutoML) 101

QuantUniversity

Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...

Sri Ambati

LinkedIn talk at Netflix ML Platform meetup Sep 2019

Faisal Siddiqi

Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016

MLconf

Automated Machine Learning

safa cimenli

Machine Learning for .NET Developers - ADC21

C3 w2

Feature Engineering

Kaggle presentation

Mining model for hotel recommendations (Kaggle Challenge)

Arjun Varma

Kaggle Higgs Boson Machine Learning Challenge

Bernard Ong

AWS Forcecast: DeepAR Predictor Time-series

PolarSeven Pty Ltd

What's hot (20)

Bayesian Global Optimization

Common Problems in Hyperparameter Optimization

Machine learning with scikitlearn

Automated Machine Learning (Auto ML)

C3 w1

Deep Dive into Hyperparameter Tuning

Winning Kaggle 101: Introduction to Stacking

Week 4 advanced labeling, augmentation and data preprocessing

Automatic machine learning (AutoML) 101

Achieving Algorithmic Transparency with Shapley Additive Explanations (H2O Lo...

LinkedIn talk at Netflix ML Platform meetup Sep 2019

Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016

Automated Machine Learning

Machine Learning for .NET Developers - ADC21

C3 w2

Feature Engineering

Kaggle presentation

Mining model for hotel recommendations (Kaggle Challenge)

Kaggle Higgs Boson Machine Learning Challenge

AWS Forcecast: DeepAR Predictor Time-series

Similar to Machine Learning Fundamentals

Accelerate Machine Learning with Ease using Amazon SageMaker

Build Your Recommendation Engine on AWS Today!

AWS Germany

Build, train and deploy your ML models with Amazon Sage Maker

AWS User Group Bengaluru

Building Applications with Apache MXNet

Apache MXNet

This deck quickly walks through fundamentals of Deep Learning and describes how symbolic engine of MXNet implements such networks. It then introduces gluon and provides code examples. The last section of the presentation introduces latest developments in gluon family of tools to include GluonNLP, an NLP toolkit with SOTA implementation of NLP algorithms, GluonCV, a Computer Vision toolkit with SOTA implementation of Vision algorithms, and MXNet backend for Keras.

Introduction to Sagemaker

ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...

Learn how you can build, train, and deploy machine learning workflows for Amazon SageMaker on AWS Step Functions. Learn how to stitch together services, such as AWS Glue, with your Amazon SageMaker model training to build feature-rich machine learning applications, and you learn how to build serverless ML workflows with less code. Cox Automotive also shares how it combined Amazon SageMaker and Step Functions to improve collaboration between data scientists and software engineers. We also share some new features to build and manage ML workflows even faster.

Amazon SageMaker Ground Truth: Build High-Quality and Accurate ML Training Da...

Successful machine learning models are built on high-quality training datasets. Labeling raw data to get accurate training datasets involves a lot of time and effort because sophisticated models can require thousands of labeled examples to learn from, before they can produce good results. Typically, the task of labeling is distributed across a large number of humans, adding significant overhead and cost. Join us as we introduce Amazon SageMaker Ground Truth, a new service that provides an effective solution to reduce this cost and complexity using a machine learning technique called active learning. Active learning reduces the time and manual effort required to do data labeling, by continuously training machine learning algorithms based on labels from humans. By iterating through ambiguous data points, Ground Truth improves the ability to automatically label data resulting in high-quality training datasets. Level: 300 Speaker: Kris Skrinak - Partner Solutions Architect, ML Global Lead, AWS

Supercharge Your ML Model with SageMaker - AWS Summit Sydney 2018

Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018

Yotam Yarden

Introducing Amazon SageMaker - AWS Online Tech Talks

Building a Recommender System on AWS

Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...

Deep learning continues to push the state of the art in domains such as computer vision, natural language understanding, and recommendation engines. One of the key reasons for this progress is the availability of highly flexible and developer friendly deep learning frameworks. In this workshop, we provide an overview of deep learning, focusing on getting started with the TensorFlow framework on AWS.

Building Your Own ML Application with AWS Lambda and Amazon SageMaker (SRV404...

In this workshop, we step through the process of deploying and hosting machine learning (ML) models with AWS Lambda and get on-demand inferences. Given a demonstrative dataset, we build and train a simple ML classification model with Amazon SageMaker. Then, we host this model in an AWS Lambda function and expose an inference endpoint through Amazon API Gateway. Finally, we build a pipeline for automating model deployment to Lambda leveraging AWS CodeBuild, AWS CodeDeploy, and AWS CodePipeline.

How Trupanion Became an AI-driven Company for Pets

DataRobot Cloud, built on AWS, helped Trupanion create an automated method for building data models using machine learning that reduced the time required to process claims from minutes to seconds. Join our webinar to hear how Trupanion transformed itself into an AI-driven organization, with robust data analysis and data science project prototyping that empowered the company to make better decisions and optimize business processes in less time and at a reduced cost. Join our webinar to learn: - Why you don’t need to be an expert in data science to create accurate predictive models. - How you can build and deploy predictive models in less time on AWS. - How to take full advantage of AI and machine learning to make better predictions faster and improve your bottom line.

A Gentle Intro to Deep Learning

Gabe Hollombe

Accelerate Machine Learning with Ease Using Amazon SageMaker - BDA301 - Chica...

Organizations are using machine learning (ML) to address a host of business challenges, from product recommendations to demand forecasting. Until recently, developing these ML models took much time and effort, and it required expertise. In this session, we discuss and dive deep into Amazon SageMaker, a fully managed ML service that enables developers and data scientists to develop and deploy deep learning models quickly and easily. We walk through the features and benefits of Amazon SageMaker and discuss the uniquely designed ML algorithms that allow for optimized model training, getting you to production fast.

Amazon SageMaker 內建機器學習演算法 (Level 400)

Work with Machine Learning in Amazon SageMaker - BDA203 - Toronto AWS Summit

Organizations are using machine learning (ML) to address a host of business challenges, from product recommendations to demand forecasting. Until recently, developing these ML models took considerable time and effort, and it required expertise. In this session, we dive deep into Amazon SageMaker, a fully managed ML service that enables developers and data scientists to develop and deploy deep learning models quickly and easily. We walk through the features and benefits of Amazon SageMaker to get your ML models from concept to production.

Quickly and easily build, train, and deploy machine learning models at any scale

AWS Germany

The machine learning process often feels a lot harder than it should be to most developers because the process to build and train models, and then deploy them into production is too complicated and too slow. This workshop starts with a brief review of the machine learning process, followed by an introduction and deep dive into the individual components of Amazon SageMaker. As part of the workshop we will train artificial neural networks, get insight into some of the built-in machine learning algorithms of SageMaker that you can use for a variety of problem types, and after successfully training a model, look at options on how to deploy and scale a model as a service. This workshop is aimed at developers that are new to machine learning, as well as data scientists that continue to be challenged by the operational challenges of the machine learning process. Bring your own laptop with Python and Jupyter Notebook, and (ideally) your own activated AWS account to follow through the examples.

How Peak.AI Uses Amazon SageMaker for Product Personalization (GPSTEC316) - A...

In this session, learn how Peak’s Artificial Intelligence System (AIS) embeds Amazon SageMaker to solve business problems with outstanding results. We show you how Peak worked backwards from two customer problems to create a machine learning (ML) solution that used multiple models, trained, and then deployed on Amazon SageMaker. We highlight the challenges, classifying PII data and integrating data from multiple sources. Next, we walk through the ML model training phase for each customer, showing you how new data sources were used to improve the accuracy of the ML models. Finally, the results: Regit and Footasylum were able to use the intelligent predictions provided by Peak.AI to deliver a personalized service to their customers, resulting in a 30% increase in revenue.

Similar to Machine Learning Fundamentals (20)

Accelerate Machine Learning with Ease using Amazon SageMaker

Build Your Recommendation Engine on AWS Today!

Build, train and deploy your ML models with Amazon Sage Maker

Building Applications with Apache MXNet

Introduction to Sagemaker

ML Workflows with Amazon SageMaker and AWS Step Functions (API325) - AWS re:I...

Amazon SageMaker Ground Truth: Build High-Quality and Accurate ML Training Da...

Supercharge Your ML Model with SageMaker - AWS Summit Sydney 2018

Build Your Recommendation Engine on AWS Today - AWS Summit Berlin 2018

Introducing Amazon SageMaker - AWS Online Tech Talks

Building a Recommender System on AWS

Building Deep Learning Applications with TensorFlow and SageMaker on AWS - Te...

Building Your Own ML Application with AWS Lambda and Amazon SageMaker (SRV404...

How Trupanion Became an AI-driven Company for Pets

A Gentle Intro to Deep Learning

Accelerate Machine Learning with Ease Using Amazon SageMaker - BDA301 - Chica...

Amazon SageMaker 內建機器學習演算法 (Level 400)

Work with Machine Learning in Amazon SageMaker - BDA203 - Toronto AWS Summit

Quickly and easily build, train, and deploy machine learning models at any scale

How Peak.AI Uses Amazon SageMaker for Product Personalization (GPSTEC316) - A...

More from SigOpt

Optimizing BERT and Natural Language Models with SigOpt Experiment Management

Experiment Management for the Enterprise

Efficient NLP by Distilling BERT and Multimetric Optimization

Detecting COVID-19 Cases with Deep Learning

Metric Management: a SigOpt Applied Use Case

Tuning for Systematic Trading: Talk 3: Training, Tuning, and Metric Strategy

Tuning for Systematic Trading: Talk 2: Deep Learning

This talk explains how to train deep learning and other expensive models with parallelism and multitask optimization to reduce wall clock time. Tobias Andreassen, who supports a number of our systematic trading customers, presented the intuition behind Bayesian optimization for model optimization with a single or multiple (often competing) metrics. Many times it makes sense to analyze a second metric to avoid myopic training runs that overfit on your data, or otherwise don’t represent or impede performance in real-world scenarios.

Tuning for Systematic Trading: Talk 1

This talk discusses the intuition behind Bayesian optimization with and without multiple metrics. Tobias Andreassen, who supports a number of our systematic trading customers, presented the intuition behind Bayesian optimization for model optimization with a single or multiple (often competing) metrics. Many times it makes sense to analyze a second metric to avoid myopic training runs that overfit on your data, or otherwise don’t represent or impede performance in real-world scenarios.

Tuning Data Augmentation to Boost Model Performance

In this webinar, SigOpt ML Engineer Meghana Ravikumar presents on and builds an image classifier trained on the Stanford Cars dataset to evaluate two approaches to transfer learning—fine tuning and feature extraction—and the impact of Multitask optimization, a more efficient form of Bayesian optimization, on these techniques. Once we define the most performant transfer learning technique for Stanford Cars, we will use image augmentation to double the size of the dataset to boost the classifier’s performance. Instead of manually tuning the hyperparameters associated with image augmentation, we will use Multitask Optimization to learn these hyperparameters using the downstream image classifier’s performance as the guide. In conjunction with model performance, we will also explore the features of these augmented images and the downstream implications for our image classifier.

Advanced Optimization for the Enterprise Webinar

Building on the TWIML eBook, TWIMLcon event and TWIML podcast series that explore Machine Learning Platforms in great detail, this webinar examines the machine learning platforms that power enterprise leaders in AI. SigOpt CEO Scott Clark will provide an overview of critical technical capabilities that our customers have prioritized in their ML platforms. Review these slides to learn about: - Critical capabilities for data, experiment and model management - Tradeoffs between building and buying these capabilities - Lessons from the implementation of these platforms by AI leaders Why focus on these platforms and the capabilities that power them? Nearly every company is investing in machine learning that differentiates products or generates revenue. These so-called "differentiated models" represent the biggest opportunity for AI to transform the business. Most of these teams find success hiring expert data scientists and machine learning engineers who can build these models. But most of these teams also struggle to create a more sustainable, scalable and reproducible process for model development, and have begun building ML platforms to tackle this challenge.

Modeling at Scale: SigOpt at TWIMLcon 2019

Tuning 2.0: Advanced Optimization Techniques Webinar

SigOpt at Ai4 Finance—Modeling at Scale

Interactive Tradeoffs Between Competing Offline Metrics with Bayesian Optimiz...

Many real world applications - machine learning models, simulators, etc. - have multiple competing metrics that define performance; these require practitioners to carefully consider potential tradeoffs. However, assessing and ranking this tradeoff is nontrivial, especially when the number of metrics is more than two. Often times, practitioners scalarize the metrics into a single objective, e.g., using a weighted sum. In this talk, we pose this problem as a constrained multi-objective optimization problem. By setting and updating the constraints, we can efficiently explore only the region of the Pareto efficient frontier of the model/system of most interest. We motivate this problem with the application of an experimental design setting, where we are trying to fabricate high performance glass substrate for solar cell panels.

Machine Learning Infrastructure

As data science workloads grow, so does their need for infrastructure. But, is it fair to ask data scientists to also become infrastructure experts? If not the data scientists, then, who is responsible for spinning up and managing data science infrastructure? This talk will address the context in which ML infrastructure is emerging, walk through two examples of ML infrastructure tools for launching hyperparameter optimization jobs, and end with some thoughts for building better tools in the future. Originally given as a talk at the PyData Ann Arbor meetup (https://www.meetup.com/PyData-Ann-Arbor/events/260380989/)

SigOpt at Uber Science Symposium - Exploring the spectrum of black-box optimi...

SigOpt at O'Reilly - Best Practices for Scaling Modeling Platforms

Companies are increasingly building modeling platforms to empower their researchers to efficiently scale the development and productionalization of their models. Scott Clark and Matt Greenwood share a case study from a leading algorithmic trading firm to illustrate best practices for building these types of platforms in any industry. Join in to learn how Two Sigma, a leading quantitative investment and technology firm, solved its model optimization problem.

SigOpt at GTC - Tuning the Untunable

Training and tuning models with lengthy training cycles like those in deep learning can be extremely expensive and may sometimes involve techniques that degrade performance. We'll explore recent research on optimization strategies to efficiently tune these types of deep learning models. We will provide benchmarks and comparisons to other popular methods for optimizing the models, and we'll recommend valuable areas for further applied research.

SigOpt at GTC - Reducing operational barriers to optimization

Advanced hardware like NVIDIA technology lowers technical barriers to model size and scope, but issues remain in areas like model performance and training infrastructure management. We'll discuss operational challenges to training models at scale with a particular focus on how training management and hyperparameter tuning can inform each other to accomplish specific goals. We'll also explore techniques like parallelism and scheduling, discuss their impact on model optimization, and compare various techniques. We'll also evaluate results of this approach. In particular, we'll focus on how new tools that automate training orchestration accelerate model development and increase the volume and quality of models in production.

Lessons for an enterprise approach to modeling at scale