📊 Data Preprocessing and Augmentation 1️⃣ Zero-Centering & Normalization Zero-Centering Given dataset: [X \in \mathbb{R}^{N \times D}] Compute mean: [\mu = \frac{1}{N} \sum_{i=1}^{N} x_...

🧠 1. Why Activation Functions Matter Without activation: [f(x) = W_2(W_1 x)] This simplifies to: [f(x) = (W_2 W_1)x] ❌ Still linear. ❌ Cannot model complex patterns. With activation: [f(x) =...

🧠 From Fully-Connected Layers to Convolutional Neural Networks (CNNs) 1️⃣ Fully-Connected (FC) Layer Definition A fully-connected layer assumes every input influences every output. Let: In...

Continuous Integration(CI) & Continuous Deployment(CD) Prerequisites 1. Git What is Continuous Integration(CI) & Continuous Deployment(CD) 1. What is Continuous Integration(CI) &...

Seq2Seq Prerequisites 1. Recurrent Neural Network <b>Recurrent Neural Network</b> have a problem that have <span style="color:#FFD5D5">rough 1:1 aligment</span>. But machi...

Gated Recurrent Units (GRU) Prerequisites 1. Recurrent Neural Network 2. LSTM <b>Recurrent Neural Network</b> have a problem when training owing to update gradient without insecure li...

Long Short Term Memory (LSTM) Prerequisites 1. Recurrent Neural Network <b>Recurrent Neural Network</b> have a problem when training owing to update gradient without insecure like <...

Recurrent Neural Network Prerequisites 1. Convolutional Neural Network <b>Convolutional Neural Network</b> is focus on spatial locality and positional invariance. It can <span styl...

Convolutional Neural Network Prerequisites 1. Multi-layer Perceptron <b>Multi-layer Perceptron</b> $ f(x) = \sigma(Wx) $ have a simple model that that <span style="color:#FFD5D5"&g...

Multi-layer Perceptrons Prerequisites 1. Linear Classifiers <b>Linear Classifiers</b> $ f(x) = Wx $ have a problem that <span style="color:#FFD5D5">FAILS on NON-LINEAR SEPERABLE...