LAMVI-2: A Visual Tool for Comparing and Tuning Word Embedding Models

10/22/2018
by   Xin Rong, et al.
0

Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one metric against another: accuracy versus overfitting, precision versus recall, smaller models and accuracy, etc. With deep learning, not only are the model's representations opaque, the model's behavior when parameters "knobs" are changed may also be unpredictable. Thus, picking the "best" model often requires time-consuming model comparison. In this work, we introduce LAMVI-2, a visual analytics system to support a developer in comparing hyperparameter settings and outcomes. By focusing on word-embedding models ("deep learning for text") we integrate views to compare both high-level statistics as well as internal model behaviors (e.g., comparing word 'distances'). We demonstrate how developers can work with LAMVI-2 to more quickly and accurately narrow down an appropriate and effective application-specific model.

READ FULL TEXT

page 6

page 10

page 12

page 13

05/30/2021

Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT

A surrogate model based hyperparameter tuning approach for deep learning...
09/10/2020

IEO: Intelligent Evolutionary Optimisation for Hyperparameter Tuning

Hyperparameter optimisation is a crucial process in searching the optima...
08/09/2020

Improving Deep Learning for Defect Prediction (using the GHOST Hyperparameter Optimizer)

There has been much recent interest in the application of deep learning ...
08/01/2021

Realised Volatility Forecasting: Machine Learning via Financial Word Embedding

We develop FinText, a novel, state-of-the-art, financial word embedding ...
07/30/2019

Ablate, Variate, and Contemplate: Visual Analytics for Discovering Neural Architectures

Deep learning models require the configuration of many layers and parame...
03/06/2020

Automatic Machine Learning Derived from Scholarly Big Data

One of the challenging aspects of applying machine learning is the need ...
10/02/2018

PromID: human promoter prediction by deep learning

Computational identification of promoters is notoriously difficult as hu...

Please sign up or login with your details

Forgot password? Click here to reset