Lale: Consistent Automated Machine Learning

2020-07-04 · Guillaume Baudart, Martin Hirzel, Kiran Kate, Parikshit Ram, Avraham Shinnar

Automated machine learning makes it easier for data scientists to develop pipelines by searching over possible choices for hyperparameters, algorithms, and even pipeline topologies. Unfortunately, the syntax for automated machine learning tools is inconsistent with manual machine learning, with each other, and with error checks. Furthermore, few tools support advanced features such as topology search or higher-order operators. This paper introduces Lale, a library of high-level Python interfaces that simplifies and unifies automated machine learning in a consistent way.

📄 PDF Abstract BibTeX arXiv:2007.01977

Code (1)

IBM/Lale.jl

Tasks

BIG-bench Machine Learning

Type-Driven Automated Learning with Lale

2019-05-24 · Martin Hirzel, Kiran Kate, Avraham Shinnar, Subhrajit Roy 외

Machine-learning automation tools, ranging from humble grid-search to hyperopt, auto-sklearn, and TPOT, help explore large search spaces of possible pipelines. Unfortunately, each of these tools has a different syntax fo…

Time Series Time Series Analysis Vocal Bursts Type Prediction

Pipeline Combinators for Gradual AutoML

2021-12-01 · NeurIPS 2021 12 · Guillaume Baudart, Martin Hirzel, Kiran Kate, Parikshit Ram 외

Automated machine learning (AutoML) can make data scientists more productive. But if machine learning is totally automated, that leaves no room for data scientists to apply their intuition. Hence, data scientists often…

AutoML BIG-bench Machine Learning Translation

LALE: Lightweight-Transformer Architecture for Land-Cover Estimation

2026-06-01 · Ümit Mert Çağlar, Alptekin Temizel arxiv

Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. Prior work typically optimizes for one of these axes: attention for glo…

Semantic Segmentation Image Segmentation

VLALeaks: Membership Inference Attacks against Vision-Language-Action Models

2026-06-13 · Xukun Luan, Jinyan Liu, Xuesong Li, Yuanguo Bi 외 arxiv

Vision-Language-Action (VLA) models enable end-to-end robot control and have garnered widespread attention. However, the memorization of training data inherent to VLA, coupled with the high cost of robotic data acquisiti…

BanglaLekha-Isolated: A Comprehensive Bangla Handwritten Character Dataset

2017-02-22 · Mithun Biswas, Rafiqul Islam, Gautam Kumar Shom, Md. Shopon 외

Bangla handwriting recognition is becoming a very important issue nowadays. It is potentially a very important task specially for Bangla speaking population of Bangladesh and West Bengal. By keeping that in our mind we a…

General Classification Handwriting Recognition