A mini project to deploy your data insight using “dash” and “visdcc” — Table of Contents · What is Graph Data? · Step 1. Define the Project Background 1. Search 2. Peek 3. Play · Step 2. Choose the Tech Stack ∘ Data wrangling ∘ Graph visualization ∘ Web hosting · Step 3. Coding Time! ∘ To start off, let’s…

You’ll never find outdated answers again — Table of Contents · Exploring Medium · Building the Dashboard 1. Search 2. Peek 3. Play · Now, It's Your Turn The year 2023 began. I wanted to write a fresh story on Medium, you know, the next big thing and whatnot. …

Complete with Branch Illustration — You’re a data scientist. As data science is becoming more and more mature every day, software engineering practices begin creeping in. You are forced to venture out of your local jupyter notebooks and meet other data scientists in the wild to build a great product. To help you out with…

Explaining their complex mathematical formula with working diagrams — Table of Contents · Recurrent Neural Networks (RNN) ∘ Vanilla RNN ∘ Long Short-term Memory (LSTM) ∘ Gated Recurrent Unit (GRU) · RNN Architectures · Attention ∘ Seq2seq with Attention ∘ Self-attention ∘ Multi-head Attention · Transformer ∘ Step 1. Adding Positional Encoding to Word Embeddings ∘ Step…

How are they better than Word2Vec? — Table of Contents 🧤 GloVe ⚙️ The Basics 🧮 Cost Function Derivation 🔮 Final Prediction 🪙 Advantages & Limitations ⏩ fastText 📚 Skip-gram reviewed 📈 Improving Skip-gram 🆚 fastText vs Word2Vec 🚀 Summary In most cases, Word2Vec embedding is better than the bag of words representation of texts by allowing…

Why Word2Vec is better, and why it’s not good enough — While image data is straightforward to be used by deep learning models (RGB value as the input), this is not the case for text data. Deep learning models only work on numbers, not sequences of symbols like texts. So, you need a way to somehow extract meaningful numerical feature vectors…

And why the heck does Inception look like a trident?! — Table of Contents · Fully Connected Layer and Activation Function · Convolution and Pooling Layer · Normalization Layer ∘ Local Response Normalization ∘ Batch Normalization · 5 Most Well-Known CNN Architectures Visualized ∘ LeNet-5 ∘ AlexNet ∘ VGG-16 ∘ Inception-v1 ∘ ResNet-50 · Wrapping Up The introduction of LeNet in…

One data, three models, detailed calculations made easy — Decision Tree is a simple model and easy to interpret. However, it is unstable because small variations in the data might result in a completely different tree being generated. It tends to overfit train data, thus has a high variance and poorly generalizes on unseen test data. This problem is…

With hands-on case study walkthroughs — There are 2 major kinds of machine learning models: supervised and unsupervised. In supervised learning, you have input data X and output data y, then the model finds a map from X to y. In unsupervised learning, you only have input data X. The goal of unsupervised learning varies: clustering…