Videos
Deep Learning, Experiment Management, Natural Language
Lessons from using SigOpt to weigh tradeoffs for BERT size and accuracyMachine Learning Engineer Meghana Ravikumar explains how she used Experiment Management to track and optimize training runs during her most recent project to effectively reduce the size of BERT.
Watch in Full ScreenExperiment Management
Experiment Management Seamless Optimization WorkflowExperiment Management
Experiment Management Editing, Updating, and Saving Visualization WidgetsExperiment Management
Experiment Management Creating Visualization WidgetsExperiment Management
Experiment Management Custom Table Filters and Linked PlotsExperiment Management
Experiment Management Linked Plots and Filtered ViewsExperiment Management
Introducing Experiment Management, Full WebinarExperiment Management
Experiment Management Visualizations, Comparisons, and WorkflowExperiment Management
Experiment Management Runs and UX ClipExperiment Management
Experiment Management Brief Summary ClipExperiment Management
Experiment Management Full WalkthroughExperiment Management
Experiment Management SynopsisAdvanced Optimization Techniques, Application, Deep Learning, Experiment Management, Modeling Best Practices, Natural Language
Efficient BERT: Find your optimal model with Multimetric Bayesian OptimizationSigOpt ML Engineer Meghana Ravikumar shares how concurrently tuning metrics like model accuracy and number of model parameters allows us to distill BERT and assess the trade-offs between model size and performance.
Watch in Full ScreenSigOpt is designed to accelerate hyperparameter optimization by intelligently trading off exploration and exploitation with an ensemble of Bayesian and global optimization algorithms that do not require access to proprietary prior insights on a model or parameters. But our users often have deep insights on their models and parameters that could guide this tuning process. Michael McCourt, Head of Research, walks through how SigOpt's newest feature Prior Beliefs to incorporated this type of prior knowledge into SigOpt’s hyperparameter optimization process.
Watch in Full ScreenAll Model Types, Multimetric Optimization, Training & Tuning
SigOpt Webinar: Introducing Metric ManagementSigOpt provides a “human-in-the-loop” process so that you can guide the platform’s discovery of a more effective set of parameters for your model, based on external business factors or domain-specific expertise. This process is called Metric Management, and is enabled by a variety of tools built into our API and web interface.
Watch in Full ScreenAdvanced Optimization Techniques, Deep Learning, Training & Tuning
Tuning for Systematic Trading: Training, Tuning and Metric StrategyIn deep learning, it can be particularly tough to select the right metric and know when a model has converged during training. In this talk, we discuss ways to monitor convergence, automate early stopping and set the right metric strategy for deep learning training and tuning jobs
Watch in Full ScreenModeling Best Practices
Tuning for Systematic Trading: Efficient deep learning and tuningSigOpt ML Engineer Tobias Andreasen shares how to efficiently tune deep learning models by using asynchronous parallelization and multitask.
Watch in Full ScreenModeling Best Practices
SigOpt Webinar: Modeling in placeModelers from Yelp, NVIDIA, Alectio and Pandora share tips for modeling remotely.
Watch in Full ScreenAdvanced Optimization Techniques, Data Augmentation, Deep Learning
SigOpt GTC 2020: Optimized Image Classification on the CheapHow can resource-constrained teams make tradeoffs between efficiency and effectiveness using pre-trained models?
Watch in Full ScreenAdvanced Optimization Techniques, All Model Types, Multimetric Optimization
Tuning for Systematic Trading: Intuition behind Bayesian optimization with and without multiple metricsTo kick off our first session of Tuning for Systematic Trading, SigOpt ML Engineer Tobias Andreasen walks us through an introduction of Bayesian optimization and some advanced features that can help you optimize model performance.
Watch in Full ScreenAdvanced Optimization Techniques, Data Augmentation, Deep Learning, Modeling Best Practices
SigOpt Webinar: Tuning Data Augmentation to Boost Model PerformanceSigOpt ML Engineer Meghana Ravikumar shares her work exploring tradeoffs between transfer learning methods, optimization strategies, and automated data augmentation.
Watch in Full ScreenAdvanced Optimization Techniques, Data Augmentation, Deep Learning
SigOpt at MLconf: Optimized Image Classification on the CheapAbstract: In this talk, we anchor on building 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 hyperparameter optimization on these techniques.
Watch in Full ScreenAdvanced Optimization Techniques, Machine Learning, Multimetric Optimization
SigOpt Webinar: Critical Capabilities of Optimization in the EnterpriseSigOpt CEO Scott Clark will provide an overview of critical technical capabilities that our customers have prioritized in their ML platforms.
Watch in Full ScreenAdvanced Optimization Techniques, All Model Types, Deep Learning, Training & Tuning
Tuning 2.0: Advanced Optimization Techniques Webinar RecordingThis webinar discusses three of SigOpt's advanced optimization techniques.
Watch in Full ScreenAll Model Types, Modeling Best Practices
SigOpt at Ai4 Finance: Modeling at ScaleThree lessons to help any enterprise scale their modeling process
Watch in Full ScreenDeep Learning, Training & Tuning
Advanced Hyperparameter Optimization for Deep Learning with MLflowBuilding on the “Best Practices for Hyperparameter Tuning with MLflow” talk, we will present advanced topics in HPO for deep learning, including early stopping, multi-metric optimization, and robust optimization.
Watch in Full ScreenAll Model Types, Modeling Best Practices
SigOpt Webinar: Modeling at Scale in Systematic TradingSigOpt works with trading firms who represent $300B in AUM. This talk draws lessons from these engagements to provide insights on how to model at scale.
Watch in Full ScreenAll Model Types, Modeling Best Practices
Best Practices for Scaling Modeling PlatformsMatt Greenwood, CIO of Two Sigma and Scott Clark, SigOpt CEO, discuss best practices for modeling at scale at O'Reilly AI
Watch in Full ScreenAugmented ML Workflow, Deep Learning
SigOpt at MLconf: Reducing Operational Barriers to Model TrainingAlexandra Johnson discusses techniques for overcoming cluster management challenges in distributed training.
Watch in Full ScreenAdvanced Optimization Techniques, Deep Learning
SigOpt at GTC: Tuning the Untunable – Lessons for Deep Learning OptimizationSigOpt presented a case study on optimizing expensive functions at GTC SJ in 2019.
Watch in Full ScreenAll Model Types, Modeling Best Practices
SigOpt at GTC: Accelerating Model Development by Reducing Operational BarriersSigOpt provided an overview of technology that makes it easy to optimize in parallel at GTC SJ in 2019.
Watch in Full ScreenAdvanced Optimization Techniques, Deep Learning
Tuning the Untunable: Insights for Deep Learning OptimizationPatrick Hayes originally gave this talk at ODSC West in 2018.
Watch in Full ScreenAll Model Types, Modeling Best Practices
Two Sigma & SigOpt Discussion on Modeling Best PracticesDuring Ai4 Finance, SigOpt CEO Scott Clark interviews SigOpt customer and CTO of Two Sigma, Matt Greenwood.
Watch in Full ScreenAdvanced Optimization Techniques, Deep Learning
Applying Multimetric Optimization to Solve Business ProblemsSigOpt CEO Scott Clark explains the value of multimetric optimization, a new capability embedded within the SigOpt Optimization Platform.
Watch in Full ScreenDeep Learning, Modeling Best Practices
Bringing Deep Learning to the CloudJoin us as we explore how SigOpt is using AWS to optimize machine learning and AI pipelines.
Watch in Full ScreenAll Model Types, Training & Tuning
Bayesian Optimization for Hyperparameter TuningSneak away and catch up with Scott Clark, Co-Founder and CEO of Sigopt, a company whose software is focused on automatically tuning your model’s parameters through Bayesian optimization.
Watch in Full ScreenApplied AI Insights, Simulations & Backtests
SigOpt for TradingLearn how you can use SigOpt to optimize your trading models.
Watch in Full ScreenApplied AI Insights, Machine Learning
SigOpt for AILearn how you can use SigOpt to optimize your AI and Machine Learning models.
Watch in Full ScreenDeep Learning, Modeling Best Practices
Using SigOpt and Tensorflow for Convolutional Neural NetworksShort tutorial on how to use SigOpt, AWS and TensorFlow to efficiently build a convolutional neural network for classifying digits in the SVHN dataset.
Watch in Full ScreenAll Model Types, Modeling Best Practices
Common Problems in Hyperparameter OptimizationCommon Problems In Hyperparameter Optimization: All large machine learning pipelines have tunable parameters, commonly referred to as hyperparameters.
Watch in Full ScreenApplied AI Insights, Simulations & Backtests
SigOpt for Algorithmic TradingDuring Ai4 Finance, SigOpt CEO Scott Clark interviews SigOpt customer and CTO of Two Sigma, Matt Greenwood.
Watch in Full ScreenApplied AI Insights, Simulations & Backtests
SigOpt for Hedge FundsIn this video I’m going to show you how SigOpt can help you amplify your trading models by optimally tuning them using our black-box optimization platform.
Watch in Full ScreenMachine Learning, Training & Tuning
Using Optimal Learning to Tune Machine Learning ModelsUsing Bayesian Optimization to Tune Machine Learning Models: In this talk we briefly introduce Bayesian Global Optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time-consuming or expensive.
Watch in Full ScreenMachine Learning, Modeling Best Practices
Visualizing Abstract Concepts in Machine LearningThere are so many exciting and new ideas to make beautiful in machine learning.
Watch in Full ScreenMachine Learning, Modeling Best Practices
Exploiting Unlabelled Data with Bayesian OptimizationIn this video, we will walk through an example that uses SigOpt to tune a machine learning pipeline for a classification task.
Watch in Full ScreenMachine Learning, Training & Tuning
Optimizing Machine Learning ModelsIn this talk we briefly introduce Bayesian Global Optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time-consuming or expensive.
Watch in Full ScreenMachine Learning, Modeling Best Practices
Using SigOpt and scikit-learn for machine learningShort tutorial on how to use SigOpt, AWS and our scikit-learn wrapper to quickly optimize the hyperparameters, train and evaluate several classification models on a given dataset.
Watch in Full ScreenDeep Learning, Modeling Best Practices
Optimizing Deep Learning ModelsBayesian Optimization methods used by SigOpt, coupled with the incredibly scalable deep learning architecture provided with the Nervana Cloud and neon, allow anyone to easily tune their models to quickly achieve higher accuracy.
Watch in Full Screen