epochlab
Dataset pathsCoursesPricingFAQAbout
Sign inGet started

Browse courses

34 courses from zero to deployed: foundation for everyone, data tracks picked by your dataset, plus the deployment gap.

Free

Python for ML

Python from zero inside Colab and Jupyter. Variables, loops, NumPy, and pandas, ready for machine learning.

About 6 hoursBeginner
Foundation

Data Understanding and Preprocessing

Explore, clean, visualize, and prepare real data. Descriptive statistics, distributions, correlation, missing values, encoding, scaling, and train test splits done right.

About 6 hoursBeginnerfrom RM5.90
Foundation

Model Evaluation and Tuning

Confusion matrix, precision, recall, F1, threshold tuning, cross validation, and hyperparameter search.

About 6 hoursIntermediatefrom RM5.90
Foundation

Deep Learning Fundamentals

Neuron to network, backprop animated, epochs, batches, learning rate, loss curves, and overfitting.

About 7 hoursBeginnerfrom RM5.90
Image

Computer Vision I

Classic computer vision with OpenCV: thresholding, filtering, edges, morphology, and contours. Learn on MNIST and CIFAR-10, then real Malaysian images. Hands-on checkpoint on PlantVillage (CC0) crop leaf disease.

About 7 hoursIntermediatefrom RM5.90
Image

Computer Vision II, Deep Learning

CNN internals, data augmentation, transfer learning with ResNet, MobileNet, and EfficientNet on Imagenette, and object detection with YOLO and the two-stage R-CNN family on the Malaysia road-sign dataset.

About 8 hoursIntermediatefrom RM5.90
Text

Text and NLP

Cleaning Malay and mixed language text, tokenization, TF-IDF, embeddings, sentiment analysis, and fine-tuning multilingual BERT.

About 7 hoursIntermediatefrom RM5.90
Video

Video and Time-Series

Frame extraction from your own phone clips, optical flow, action recognition, and LSTM or GRU on UCI HAR sensor data. Malaysia angle: Bahasa Isyarat Malaysia (BIM-SSD).

About 7 hoursAdvancedfrom RM5.90
Tabular

Tabular

Feature engineering and selection, XGBoost and LightGBM, and SHAP explainability for real tabular problems.

About 6 hoursAdvancedfrom RM5.90
Foundation

Reinforcement Learning

Teach agents to learn from reward. Markov decision processes, Q-learning, and where reinforcement learning fits in the ML landscape.

About 3 hoursBeginnerfrom RM5.90
Deployment

Big Data Engineering

Handle data at scale. Distributed storage, MapReduce, Spark, and parallel processing for datasets too big for one machine.

About 4 hoursBeginnerfrom RM5.90
Deployment

Model Deployment

Save and load models, build a FastAPI service, connect to a web app, cloud free tiers, and Docker basics.

About 6 hoursAdvancedfrom RM5.90
Deployment

Optimization for Production

Quantization FP32 to INT8, pruning, ONNX, TensorFlow Lite, latency vs accuracy, batch inference, caching, and monitoring.

About 6 hoursAdvancedfrom RM5.90
Capstone

Capstone, End-to-End ML Project

Bring everything together: take a Kaggle dataset from a raw CSV to a deployed model, and earn your overall EpochLab certificate.

About 2 hoursAdvancedfrom RM5.90
Free

Machine Learning Foundations

What it means for a model to learn, plus loss and gradient descent. The intuition before any algorithm, capped by a hands-on checkpoint. Free.

About 1 hoursBeginner
Foundation

Linear Regression

Fit a straight line to predict a continuous number. The classic first ML algorithm.

About 1 hoursBeginnerfrom RM5.90
Foundation

Logistic Regression

Turn features into a probability for a yes or no decision. A fast, interpretable classifier.

About 1 hoursBeginnerfrom RM5.90
Foundation

Ridge and Lasso

Regularized regression that curbs overfitting, and Lasso can select features for you.

About 1 hoursBeginnerfrom RM5.90
Foundation

K-Nearest Neighbors

Classify a point by the labels of its nearest neighbors. Simple, no real training.

About 1 hoursBeginnerfrom RM5.90
Foundation

Naive Bayes

A fast probabilistic classifier that shines on text and spam detection.

About 1 hoursBeginnerfrom RM5.90
Foundation

Decision Tree

Learn readable if-then rules from data, the building block of forests and boosting.

About 1 hoursBeginnerfrom RM5.90
Foundation

Random Forest

An ensemble of trees that vote together for a strong, robust tabular prediction.

About 1 hoursBeginnerfrom RM5.90
Foundation

Gradient Boosting

Build trees that fix each other's errors for top tabular accuracy (XGBoost, LightGBM).

About 1 hoursBeginnerfrom RM5.90
Foundation

Support Vector Machine

Find the widest margin between classes, with kernels for non-linear boundaries.

About 1 hoursBeginnerfrom RM5.90
Foundation

K-Means Clustering

Group unlabeled data into k clusters by nearest centroid. The go-to first clustering method.

About 1 hoursBeginnerfrom RM5.90
Foundation

Hierarchical Clustering

Build a tree of nested clusters (a dendrogram) and cut it wherever you like.

About 1 hoursBeginnerfrom RM5.90
Foundation

DBSCAN

Density-based clustering that finds any-shape clusters and flags outliers as noise.

About 1 hoursBeginnerfrom RM5.90
Foundation

Principal Component Analysis

Compress many correlated features into a few directions of greatest variance.

About 1 hoursBeginnerfrom RM5.90
Foundation

Convolutional Neural Network (CNN)

How CNNs read images: convolution, filters, pooling, and the feature maps behind modern computer vision.

About 1 hoursBeginnerfrom RM5.90
Foundation

Neural Network (MLP)

The feedforward neural network: neurons, layers, activations, and backpropagation, the base of all deep learning.

About 1 hoursBeginnerfrom RM5.90
Foundation

Recurrent Networks and LSTM

Networks with memory for sequences and time-series, and how LSTM gates beat the vanishing gradient.

About 1 hoursBeginnerfrom RM5.90
Foundation

Transformers and Attention

Self-attention and the architecture behind modern NLP and large language models.

About 1 hoursBeginnerfrom RM5.90
Foundation

Autoencoders

Unsupervised encoder-decoder networks for compression, denoising, and anomaly detection.

About 1 hoursBeginnerfrom RM5.90
Foundation

Gaussian Mixture Models (GMM)

Soft, probabilistic clustering with the EM algorithm, for overlapping and elliptical groups.

About 1 hoursBeginnerfrom RM5.90

Not sure where to start?

Learn by dataset. Tell us what data you have: image, text, video, or tabular, and we map the exact course path for you.

Choose my dataset