PinnedPublished inTowards Data Science1x1 Convolution: DemystifiedShedding light on the concept of 1x1 convolution operation which appears in paper, Network in Network by Lin et al. and Google InceptionFeb 19, 20211Feb 19, 20211
PinnedPublished inTowards Data ScienceVariational Bayes: the intuition behind Variational Auto-Encoders (VAEs).The high computational cost of inferring from a complicated and often intractable, ‘true posterior distribution’ has always been a…Jan 22, 20214Jan 22, 20214
PinnedPublished inTowards Data ScienceKalman Filtering: An Intuitive Guide Based on Bayesian ApproachConceptualising Kalman Filtering using Bayesian thinkingDec 10, 20203Dec 10, 20203
PinnedPublished inTowards Data ScienceTo or not to SMOTE?If a picture says a thousand words, your data probably says a lot more! You just need to listen. An article on Synthetic Over-SamplingNov 22, 2020Nov 22, 2020
PinnedPublished inThe StartupThinking GenerativelyIn minimising the error in our ML models, the benefits of intentionally incorporating errors or noise into our models is often overlooked!Nov 13, 2020Nov 13, 2020
Data Scientist’s Guide to Effective Self-Promotion: Boost your online presence with simple…How to effectively self-promote as a data scientist. Showcase your work, build your brand, and collaborate.Apr 30, 2023Apr 30, 2023
Published inTowards Data ScienceModelling Physiological Signal Estimation as a Deep Learning ProblemMay 3, 2021May 3, 2021
Published inArtificial Intelligence in Plain EnglishImage Classification in a Single Dimension using MNIST 1-DMNIST 1-D is an interesting dataset that challenged the status quo by providing a low-cost, low-resource alternative to MNIST image…Mar 4, 2021Mar 4, 2021