DrivenData Labs

APRIL 10, 2024

Model architectures : All four winners created ensembles of deep learning models and relied on some combination of UNet, ConvNext, and SWIN architectures. In the modeling phase, XGBoost predictions serve as features for subsequent deep learning models. Test-time augmentations were used with mixed results.

Deep Learning 130

Deep Learning Deep Learning Machine Learning Machine Learning 130

Towards AI

JULY 19, 2023

This is part 2, and you will learn how to do sales prediction using Time Series. Please refer to Part 1– to understand what is Sales Prediction/Forecasting, the Basic concepts of Time series modeling, and EDA I’m working on Part 3 where I will be implementing Deep Learning and Part 4 where I will be implementing a supervised ML model.

Cross Validation 98

Cross Validation Clustering EDA Data Preparation 98

Pickl AI

JULY 12, 2024

Summary: This guide explores Artificial Intelligence Using Python, from essential libraries like NumPy and Pandas to advanced techniques in machine learning and deep learning. TensorFlow and Keras: TensorFlow is an open-source platform for machine learning.

Artificial Intelligence 52

Artificial Intelligence Artificial Intelligence Python Natural Language Processing 52

Pickl AI

FEBRUARY 12, 2024

What is cross-validation, and why is it used in Machine Learning? Cross-validation is a technique used to assess the performance and generalization ability of Machine Learning models. What is the Central Limit Theorem, and why is it important in statistics?

Data Science 52

Data Science Cross Validation Machine Learning Machine Learning 52

Pickl AI

DECEMBER 16, 2024

Exploratory Data Analysis (EDA): Conduct EDA to identify trends, seasonal patterns, and correlations within the dataset. Split the Data: Divide your dataset into training, validation, and testing subsets to ensure robust evaluation. Making Data Stationary: Many forecasting models assume stationarity.

AI 52

AI AI Machine Learning Machine Learning 52

Heartbeat

MAY 29, 2023

It is therefore important to carefully plan and execute data preparation tasks to ensure the best possible performance of the machine learning model. It is also essential to evaluate the quality of the dataset by conducting exploratory data analysis (EDA), which involves analyzing the dataset’s distribution, frequency, and diversity of text.

Machine Learning 78

Machine Learning Machine Learning Natural Language Processing Data Preparation 78

Pickl AI

SEPTEMBER 12, 2024

Clustering: An unsupervised Machine Learning technique that groups similar data points based on their inherent similarities. Cross-Validation: A model evaluation technique that assesses how well a model will generalise to an independent dataset.

Data Analyst 52

Data Analyst Data Science Machine Learning Machine Learning 52