Open in app

Sign in

Write

Sign in

Satyam Kumar
Satyam Kumar

4.8K Followers

Home

About

Published in

Towards AI

·Aug 14

The Unreasonable Effectiveness of Transfer Learning

Essential guide to multi-output prediction with Keras Functional API — Training a complex deep-learning neural network requires significant computational efficiency, the availability of a large corpus of data, and better feature learning architecture to achieve state-of-the-art results. But these requirements are only sometimes satisfied for start-ups, researchers, and students. …

Artificial Intelligence

4 min read

The Unreasonable Effectiveness of Transfer Learning
The Unreasonable Effectiveness of Transfer Learning
Artificial Intelligence

4 min read


Published in

Artificial Intelligence in Plain English

·Aug 1

Are you plotting the correct Elbow plot to find the optimal number of clusters?

Essential guide to various clustering evaluation metrics — Clustering is an unsupervised machine-learning approach to divide the population into groups or clusters such that the samples assigned to the same cluster share similar properties, and samples assigned to different clusters are different from each other. There are various popular clustering techniques including k-Means clustering which is a centroid-based…

Machine Learning

5 min read

Are you plotting the correct Elbow plot to find the optimal number of clusters?
Are you plotting the correct Elbow plot to find the optimal number of clusters?
Machine Learning

5 min read


Published in

Towards Data Science

·Apr 19

Top 10 Pre-Trained Models for Image Embedding every Data Scientist Should Know

Essential guide to transfer learning — The rapid developments in Computer Vision — image classification use cases have been further accelerated by the advent of transfer learning. It takes a lot of computational resources and time to train a computer vision neural network model on a large dataset of images. Luckily, this time and resources can…

Artificial Intelligence

9 min read

Top 10 Pre-Trained Models for Image Embedding every Data Scientist Should Know
Top 10 Pre-Trained Models for Image Embedding every Data Scientist Should Know
Artificial Intelligence

9 min read


Published in

Towards Data Science

·Mar 7

5 Changepoint Detection algorithms every Data Scientist should know

Essential guide to changepoint detection algorithms for time series analysis — Time-series analytics is one of the topics a data scientist must have exposure to. Time-series analysis comprises the process and mathematical set of tools used for looking into time-series data to learn what happened, when and why it happened, and what is most likely to occur in the future. Change…

Artificial Intelligence

3 min read

5 Changepoint Detection algorithms every Data Scientist should know
5 Changepoint Detection algorithms every Data Scientist should know
Artificial Intelligence

3 min read


Published in

Towards Data Science

·Feb 6

14 Techniques to make your Pandas workflow lighting fast

Essential guide to scale-up your Pandas workflow — Pandas is one of the most popular Python libraries for data exploration and visualization. Pandas offer tons of APIs to perform data-wrangling tasks, but when working with large datasets, it fails or has slow computations. In this article, we will discuss 14 techniques to speed up the Pandas workflow using…

Artificial Intelligence

6 min read

14 Techniques to make your Pandas workflow lighting fast
14 Techniques to make your Pandas workflow lighting fast
Artificial Intelligence

6 min read


Published in

Towards Data Science

·Jan 31

Bi-LSTM+Attention for Modeling EHR Data

Essential guide to the diagnosis prediction in healthcare via attention-based Bi-LSTM network — Predicting future health information or disease using the Electronic Health Record (EHR) is a key use case for research in the healthcare domain. EHR data consists of diagnosis codes, pharmacy codes, and procedure codes. …

Artificial Intelligence

7 min read

Bi-LSTM+Attention for Modeling EHR Data
Bi-LSTM+Attention for Modeling EHR Data
Artificial Intelligence

7 min read


Published in

Towards Data Science

·Sep 5, 2022

Improve Time Series Forecasting performance with the Facebook Prophet model

Essential guide to time series feature engineering and forecasting — Time series forecasting involves model building on historical time-stamped data values and external factors to make scientific predictions that drive future strategic decision-making. Training a robust time-series forecasting model for accurate and reliable predictions is one of the most challenging tasks, given its direct impact on related decisions. …

Artificial Intelligence

4 min read

Improve Time Series Forecasting performance with the Facebook Prophet model
Improve Time Series Forecasting performance with the Facebook Prophet model
Artificial Intelligence

4 min read


Published in

Towards Data Science

·Aug 23, 2022

Automate the Feature Engineering Pipeline for Your Relational Dataset

Essential guide to an open-source Python framework for automated feature engineering — Feature engineering is an important and time-consuming component of the data science model development pipeline. The feature engineering pipeline decides the robustness and performance of the model. There are various automated feature engineering packages that process and create features for a single dataset. But these packages fail for the use-cases…

Artificial Intelligence

3 min read

Automate the Feature Engineering Pipeline for Your Relational Dataset
Automate the Feature Engineering Pipeline for Your Relational Dataset
Artificial Intelligence

3 min read


Published in

Towards Data Science

·Aug 17, 2022

Time Series Forecasting made easy with Darts

An open-source package for time series preprocessing and forecasting with unified and user-friendly APIs — Time series forecasting involves model building on historical time-stamped data to make scientific predictions and drive future strategic decision-making. Time series forecasting has many uses in various domains including: Predict consumer demand for every product Forecasting pandemic spread, diagnosis, medication, and planning in healthcare

Artificial Intelligence

3 min read

Time Series Forecasting made easy with Darts
Time Series Forecasting made easy with Darts
Artificial Intelligence

3 min read


Published in

Towards Data Science

·Aug 11, 2022

Automate Time Series Feature Engineering in a few lines of Python Code

Extract hundreds of relevant features for your time series use-case — Time Series data capture the variable's value repeatedly over time resulting in a series of data points indexed in time order. In time series data has natural temporal ordering i.e. the value of a variable at a particular time is dependent on past values. Traditional machine learning algorithms are not…

Artificial Intelligence

3 min read

Automate Time Series Feature Engineering in a few lines of Python Code
Automate Time Series Feature Engineering in a few lines of Python Code
Artificial Intelligence

3 min read

Satyam Kumar

Satyam Kumar

4.8K Followers

Data Scientist | 3.5 M+ Views | Connect: https://www.linkedin.com/in/satkr/ | Unlimited Reads: https://satyam-kumar.medium.com/membership

Following
  • ODSC - Open Data Science

    ODSC - Open Data Science

  • Dario Radečić

    Dario Radečić

  • TDS Editors

    TDS Editors

  • Ahmed Besbes

    Ahmed Besbes

  • Soner Yıldırım

    Soner Yıldırım

See all (40)

Help

Status

About

Careers

Blog

Privacy

Terms

Text to speech

Teams