Adam Nelson

Australia

Featured in: Favicon

nature.com Favicon

rsc.org

towardsdatascience.com Favicon

flyertalk.com Favicon

bioprocessintl.com Favicon

towardsai.net Favicon

pubs.rsc.org

Articles

Temperature-induced mobility in octacalcium phosphate impacts crystal symmetry: water dynamics studied by NMR crystallography

Jan 9, 2025 | pubs.rsc.org | Adam Nelson |Univ Montpellier |Wassilios Papawassiliou

Temperature-induced mobility in octacalcium phosphate impacts crystal symmetry: water dynamics studied by NMR crystallography† Octacalcium phosphate (OCP, Ca8(PO4)4(HPO4)2·5H2O) is a notable calcium phosphate due to its biocompatibility, making it a widely studied material for bone substitution. It is known to be a precursor of bone mineral, but its role in biomineralisation remains unclear.
Programming A Neural Network: Regression in Keras

Oct 28, 2024 | pub.towardsai.net | Adam Nelson

A detailed tutorial and walk through classic house price predictionAs you move through your data science learning journey it is important to balance the time you spend on learning theory against the time you spend on learning to code, apply, or implement. I am a strong proponent of not racing to the .predict() method. Previously I have warned that many data science bootcamps (and by implication also tutorials) operate or feel like a race to the .predict() method.
Programming a Neural Network Tutorial: Backward Propagation

Oct 1, 2024 | towardsai.net | Adam Nelson

Last Updated on October 5, 2024 by Originally published on Towards AI. Densely connected artificial neural network learning processesThis member-only story is on us. Upgrade to access all of Medium. To fully understand the theory of how neural networks learn you have to have a close look at backward propagation. This tutorial provides that close look.
Advance Slicing And Indexing + Numpy Array Walkthrough

Sep 19, 2024 | towardsai.net | Adam Nelson

Last Updated on September 27, 2024 by Originally published on Towards AI. Exploring advanced slicing techniques with Numpy, skimage, + PythonThis member-only story is on us. Upgrade to access all of Medium. When working with NumPy arrays, mastering advanced slicing techniques can greatly enhance your data manipulation capabilities. In this article, we’ll walk through common indexing and slicing approaches.
Programming a Neural Network Tutorial: Vintage Style

Dec 10, 2023 | pub.towardsai.net | Adam Nelson

Underlying math of neural networks by studying our predecessor’s waysOne of the first to describe neural networks was neurophysiologis Warren McCulloch and mathematician Walter Pitts, as a model for biological brains. In 1959 Bernard Widrow and Marcian Hoff of Stanford adapted the idea to create MADALINE, the first neural network put into production to eliminate echoes in phone lines. It’s still in use today! (Stanford History of Neural Networks).
MakeBlobs + Fictional Synthetic Data A New(ish) Use Case

Nov 23, 2023 | pub.towardsai.net | Adam Nelson

Image Credit: ODSC Conference. Four panelists speaking about synthetic data including, Ali Golshan, Jay Alammar, Sheamus McGovern, and Yashar Behzadi. Image used with permission. From the west edition of the Open Data Science Conference (ODSC), one of the "buzziest" panels was on the topic of synthetic data. This article revisits that topic with a new look at how you can quickly spin out a new fictional data set with make_blobs.
Reducing Risk in Prepacked Chromatography Columns - BioProcess International

Nov 16, 2023 | bioprocessintl.com | Adam Nelson

Figure 1: More than 1,000 data points demonstrate reproducible ion-exchange (IEX) resin packing while maintaining robust quality across eight years. Red lines denote upper and lower confidence limits, with 99% <3σ and 96% <2σ for efficiency, and 98% <2σ and 99% <3σ for asymmetry. rHETP = reduced height equivalent of theoretical plate.
The Good, The Bad, and the Ugly of Pd.Get_Dummies

Jul 26, 2023 | towardsdatascience.com | Adam Nelson

This is for the pd.get_dummies diehardsHowdy folks 🤠Okay, I get it. One of the easiest ways to convert a categorial to an array of dummies in Python is with the Pandas pd.get_dummies(). Why would you take the time to import OneHotEncoderfrom sklearn, execute a .fit_transform() etc, etc, etc? Talk about tedious!This article will first introduce a simple data set for demonstration purposes that consists of a testing set that contains categoricals not found in the training set.
The Good, The Bad, and the Ugly of Pd.Get_Dummies

Jul 26, 2023 | towardsdatascience.com | Adam Nelson

Howdy folks 🤠Okay, I get it. One of the easiest ways to convert a categorial to an array of dummies in Python is with the Pandas pd.get_dummies(). Why would you take the time to import OneHotEncoderfrom sklearn, execute a .fit_transform() etc, etc, etc? Talk about tedious!Image Credit: Author's illustration using text to image in Canva.
Inspecting Data Science Predictions: Individual + Negative Case Analysis

Jul 21, 2023 | towardsdatascience.com | Adam Nelson

How to inspect specific predictions and conduct negative case analysesSomewhere around 40 to 43% of the time when I am showing new learners how to use the .predict() methods I get the following question:Where are the predictions? I wish this was a question learners would ask more often. It is an insightful question, especially for folks who are newer to Python, data science, and who may be seeing the .predict() method for the first time.