Code N Curry MLCode & Curry ML

Neural Soup Roadmap

VERSION 2.4 · BLUEPRINT PHASE

Season by season. Ek ek karke. No rush.

S0: Welcome & Setup

0.2

Set Up Your Free Lab

🔒
TIME: —YIELD: 100XP
0.3

How to Learn ML Without Burning Out

🔒
TIME: —YIELD: 100XP

S1: Python for ML

1.1

Variables, Types & Print

🔒
TIME: —YIELD: 100XP
1.2

Lists, Dicts & Sets

🔒
TIME: —YIELD: 100XP
1.3

Conditions & Comparisons

🔒
TIME: —YIELD: 100XP
1.4

Loops (for & while)

🔒
TIME: —YIELD: 100XP
1.5

Functions

🔒
TIME: —YIELD: 100XP
1.6

NumPy Basics

🔒
TIME: —YIELD: 100XP
1.7

Pandas Basics

🔒
TIME: —YIELD: 100XP
1.8

Plotting with Matplotlib

🔒
TIME: —YIELD: 100XP
1.9

Reading Real Data Files

🔒
TIME: —YIELD: 100XP
1.10

Mini-Project: Personal Data Dashboard

🔒
TIME: —YIELD: 100XP

S2: Maths You Actually Need

2.1

Why Maths in ML?

🔒
TIME: —YIELD: 100XP
2.2

Vectors & Matrices

🔒
TIME: —YIELD: 100XP
2.3

Mean, Median, Variance, Std

🔒
TIME: —YIELD: 100XP
2.4

Probability Basics

🔒
TIME: —YIELD: 100XP
2.5

Distributions

🔒
TIME: —YIELD: 100XP
2.6

Functions, Slopes & Gradients

🔒
TIME: —YIELD: 100XP
2.7

Gradient Descent (Intuition)

🔒
TIME: —YIELD: 100XP
2.8

Distance & Similarity

🔒
TIME: —YIELD: 100XP
2.9

Maths Recap Quiz

🔒
TIME: —YIELD: 100XP

S3: Data Wrangling & EDA

3.1

The ML Workflow, End to End

🔒
TIME: —YIELD: 100XP
3.2

Loading & Inspecting Data

🔒
TIME: —YIELD: 100XP
3.3

Handling Missing Values

🔒
TIME: —YIELD: 100XP
3.4

Categorical Data & Encoding

🔒
TIME: —YIELD: 100XP
3.5

Feature Scaling

🔒
TIME: —YIELD: 100XP
3.6

EDA: Finding the Story in Data

🔒
TIME: —YIELD: 100XP
3.7

Correlation & Feature Relationships

🔒
TIME: —YIELD: 100XP
3.8

Train/Test Split & Data Leakage

🔒
TIME: —YIELD: 100XP

S4: Core ML: Supervised Learning

4.1

Your First Model: Linear Regression

🔒
TIME: —YIELD: 100XP
4.2

Evaluating Regression (MAE, RMSE, R²)

🔒
TIME: —YIELD: 100XP
4.3

Logistic Regression (Classification)

🔒
TIME: —YIELD: 100XP
4.4

Classification Metrics & Confusion Matrix

🔒
TIME: —YIELD: 100XP
4.5

K-Nearest Neighbours

🔒
TIME: —YIELD: 100XP
4.6

Decision Trees

🔒
TIME: —YIELD: 100XP
4.7

Random Forests

🔒
TIME: —YIELD: 100XP
4.8

Naive Bayes (Text Classification)

🔒
TIME: —YIELD: 100XP
4.9

Support Vector Machines (Intuition)

🔒
TIME: —YIELD: 100XP
4.10

Gradient Boosting & XGBoost

🔒
TIME: —YIELD: 100XP
4.11

Overfitting vs Underfitting

🔒
TIME: —YIELD: 100XP
4.12

Mini-Project: End-to-End Predictor

🔒
TIME: —YIELD: 100XP

S5: Unsupervised Learning

5.1

What Is Unsupervised Learning?

🔒
TIME: —YIELD: 100XP
5.2

K-Means Clustering

🔒
TIME: —YIELD: 100XP
5.3

Choosing k (Elbow Method)

🔒
TIME: —YIELD: 100XP
5.4

Dimensionality Reduction (PCA)

🔒
TIME: —YIELD: 100XP
5.5

Mini-Project: Customer Segments

🔒
TIME: —YIELD: 100XP

S6: Model Quality & Tuning

6.1

Cross-Validation

🔒
TIME: —YIELD: 100XP
6.2

Hyperparameter Tuning

🔒
TIME: —YIELD: 100XP
6.3

Pipelines

🔒
TIME: —YIELD: 100XP
6.4

Handling Imbalanced Data

🔒
TIME: —YIELD: 100XP
6.5

Feature Engineering

🔒
TIME: —YIELD: 100XP
6.6

Feature Importance & Explainability

🔒
TIME: —YIELD: 100XP
6.7

Saving & Loading Models

🔒
TIME: —YIELD: 100XP

S7: Real-World Projects

7.1

S7E1–E2 — Project: House / Car Price Predictor

🔒
TIME: —YIELD: 100XP
7.3

S7E3–E4 — Project: Spam / Sentiment Classifier

🔒
TIME: —YIELD: 100XP
7.5

S7E5–E6 — Project: Deploy a Model as a Web App

🔒
TIME: —YIELD: 100XP

S8: Advanced ML + Deep Learning

8.1

Ensemble Methods Deep-Dive

🔒
TIME: —YIELD: 100XP
8.2

Time Series Basics

🔒
TIME: —YIELD: 100XP
8.3

Recommendation Systems (Intro)

🔒
TIME: —YIELD: 100XP
8.4

Intro to NLP

🔒
TIME: —YIELD: 100XP
8.5

What Is a Neural Network? (Intuition)

🔒
TIME: —YIELD: 100XP
8.6

Your First Neural Net (Keras)

🔒
TIME: —YIELD: 100XP
8.7

When to Use ML vs Deep Learning

🔒
TIME: —YIELD: 100XP
8.8

Season Finale + The Road to DL & AI

🔒
TIME: —YIELD: 100XP
VIEW YOUR DASHBOARD →