[
  {
    "id": "c001",
    "slug": "intro-neural-networks",
    "title": "Introduction to Neural Networks",
    "category": "Foundations",
    "level": "Beginner",
    "price": 79,
    "rating": 4.7,
    "duration_hours": 10,
    "students": 4200,
    "short": "Build intuition for perceptrons, activations, and basic training loops.",
    "description": "Learn the building blocks of neural networks, from perceptrons to multilayer networks, including activation functions and loss minimization.",
    "tags": ["Foundations", "neural networks", "backprop"],
    "prerequisites": ["Basic Python"],
    "release": "2024-01-10",
    "updated": "2026-02-01"
  },
  {
    "id": "c002",
    "slug": "backpropagation-from-scratch",
    "title": "Backpropagation From Scratch",
    "category": "Foundations",
    "level": "Beginner",
    "price": 89,
    "rating": 4.8,
    "duration_hours": 12,
    "students": 3900,
    "short": "Derive and implement backpropagation in pure Python and NumPy.",
    "description": "Step-by-step derivations and code to demystify backpropagation, gradients, and autograd-like mechanics.",
    "tags": ["Foundations", "gradients", "autograd"],
    "prerequisites": ["Python", "Calculus"],
    "release": "2024-03-05",
    "updated": "2026-01-20"
  },
  {
    "id": "c003",
    "slug": "optimization-deep-learning",
    "title": "Optimization for Deep Learning",
    "category": "Optimization",
    "level": "Intermediate",
    "price": 109,
    "rating": 4.6,
    "duration_hours": 14,
    "students": 2100,
    "short": "Understand SGD, momentum, Adam, schedulers, and generalization.",
    "description": "Covers key optimizers, initialization, normalization, and strategies for stable and fast convergence.",
    "tags": ["optimization", "SGD", "Adam", "generalization"],
    "prerequisites": ["Linear Algebra", "Calculus"],
    "release": "2024-05-22",
    "updated": "2026-02-10"
  },
  {
    "id": "c004",
    "slug": "convolutional-neural-networks",
    "title": "Convolutional Neural Networks",
    "category": "Computer Vision",
    "level": "Intermediate",
    "price": 119,
    "rating": 4.7,
    "duration_hours": 16,
    "students": 3300,
    "short": "Design and train CNNs for image classification and detection.",
    "description": "Covers convolution, pooling, modern architectures, and training strategies for robust image models.",
    "tags": ["CNN", "Computer Vision"],
    "prerequisites": ["Python", "Linear Algebra"],
    "release": "2024-06-15",
    "updated": "2026-02-02"
  },
  {
    "id": "c005",
    "slug": "recurrent-networks",
    "title": "Recurrent Networks: RNN, LSTM, GRU",
    "category": "NLP",
    "level": "Intermediate",
    "price": 115,
    "rating": 4.5,
    "duration_hours": 15,
    "students": 2700,
    "short": "Sequence modeling with RNNs, LSTMs, and GRUs for text.",
    "description": "Implement recurrent architectures and train models for language modeling and sequence prediction.",
    "tags": ["RNN", "LSTM", "sequence", "NLP"],
    "prerequisites": ["Python", "Probability"],
    "release": "2024-04-20",
    "updated": "2026-01-25"
  },
  {
    "id": "c006",
    "slug": "attention-transformers",
    "title": "Attention and Transformers",
    "category": "NLP",
    "level": "Advanced",
    "price": 149,
    "rating": 4.9,
    "duration_hours": 18,
    "students": 5200,
    "short": "Master attention mechanisms and build transformer models.",
    "description": "From scaled dot-product attention to transformer blocks, pretraining, and fine-tuning.",
    "tags": ["Transformers", "attention", "NLP"],
    "prerequisites": ["Linear Algebra", "Optimization"],
    "release": "2024-08-01",
    "updated": "2026-02-12"
  },
  {
    "id": "c007",
    "slug": "graph-neural-networks",
    "title": "Graph Neural Networks",
    "category": "Foundations",
    "level": "Advanced",
    "price": 139,
    "rating": 4.6,
    "duration_hours": 16,
    "students": 1700,
    "short": "Message passing, GCN, GAT, and scalable GNN training.",
    "description": "Learn graph representations, convolution on graphs, and real-world applications.",
    "tags": ["GNN", "graphs"],
    "prerequisites": ["Linear Algebra", "Python"],
    "release": "2024-09-10",
    "updated": "2026-02-10"
  },
  {
    "id": "c008",
    "slug": "regularization-techniques",
    "title": "Regularization Techniques",
    "category": "Optimization",
    "level": "Intermediate",
    "price": 99,
    "rating": 4.4,
    "duration_hours": 10,
    "students": 1600,
    "short": "Dropout, weight decay, data augmentation, and early stopping.",
    "description": "Reduce overfitting with robust tricks and principled methods.",
    "tags": ["regularization", "dropout", "augmentation"],
    "prerequisites": ["Calculus"],
    "release": "2024-07-05",
    "updated": "2026-02-03"
  },
  {
    "id": "c009",
    "slug": "unsupervised-learning",
    "title": "Unsupervised Representation Learning",
    "category": "Foundations",
    "level": "Advanced",
    "price": 129,
    "rating": 4.5,
    "duration_hours": 14,
    "students": 1500,
    "short": "Autoencoders, contrastive learning, and clustering.",
    "description": "Learn feature learning without labels and modern self-supervised methods.",
    "tags": ["autoencoders", "contrastive", "SSL"],
    "prerequisites": ["Probability", "Linear Algebra"],
    "release": "2024-11-18",
    "updated": "2026-01-30"
  },
  {
    "id": "c010",
    "slug": "generative-models-gan",
    "title": "Generative Models: GANs",
    "category": "Generative",
    "level": "Advanced",
    "price": 149,
    "rating": 4.6,
    "duration_hours": 16,
    "students": 2300,
    "short": "Adversarial training, stability tricks, and metrics.",
    "description": "Build and evaluate GANs with focus on convergence and sample quality.",
    "tags": ["GAN", "generative"],
    "prerequisites": ["Optimization", "Python"],
    "release": "2024-12-12",
    "updated": "2026-02-05"
  },
  {
    "id": "c011",
    "slug": "diffusion-models",
    "title": "Diffusion Models",
    "category": "Generative",
    "level": "Advanced",
    "price": 159,
    "rating": 4.8,
    "duration_hours": 20,
    "students": 3100,
    "short": "Forward and reverse processes, UNets, and guidance.",
    "description": "Implement diffusion models from scratch and understand noise schedules.",
    "tags": ["diffusion", "generative", "UNet"],
    "prerequisites": ["Calculus", "Optimization"],
    "release": "2025-01-20",
    "updated": "2026-02-10"
  },
  {
    "id": "c012",
    "slug": "mlops-production",
    "title": "MLOps and Production",
    "category": "Production",
    "level": "Intermediate",
    "price": 129,
    "rating": 4.5,
    "duration_hours": 12,
    "students": 2800,
    "short": "From training to serving: monitoring, drift, and CI/CD.",
    "description": "Deploy and maintain models reliably with versioning and observability.",
    "tags": ["MLOps", "production"],
    "prerequisites": ["Python"],
    "release": "2025-02-14",
    "updated": "2026-02-11"
  },
  {
    "id": "c013",
    "slug": "model-interpretability",
    "title": "Model Interpretability",
    "category": "Foundations",
    "level": "Intermediate",
    "price": 99,
    "rating": 4.4,
    "duration_hours": 10,
    "students": 1400,
    "short": "Saliency, SHAP, counterfactuals, and fairness basics.",
    "description": "Explain predictions and assess potential biases with practical tools.",
    "tags": ["interpretability", "fairness"],
    "prerequisites": ["Probability"],
    "release": "2025-03-05",
    "updated": "2026-02-06"
  },
  {
    "id": "c014",
    "slug": "nlp-tokenization-embeddings",
    "title": "NLP: Tokenization and Embeddings",
    "category": "NLP",
    "level": "Beginner",
    "price": 89,
    "rating": 4.6,
    "duration_hours": 12,
    "students": 3600,
    "short": "Subword tokenization, word2vec, GloVe, and modern embeddings.",
    "description": "Text preprocessing and representation techniques for downstream tasks.",
    "tags": ["tokenization", "embeddings", "NLP"],
    "prerequisites": ["Python"],
    "release": "2025-03-30",
    "updated": "2026-02-08"
  },
  {
    "id": "c015",
    "slug": "computer-vision-augmentations",
    "title": "Data Augmentations for Vision",
    "category": "Computer Vision",
    "level": "Intermediate",
    "price": 99,
    "rating": 4.5,
    "duration_hours": 10,
    "students": 1900,
    "short": "Design robust augmentation pipelines for strong generalization.",
    "description": "Theory and practice of augmentations, mixup, cutout, and RandAugment.",
    "tags": ["augmentation", "vision", "CNN"],
    "prerequisites": ["Python"],
    "release": "2025-04-18",
    "updated": "2026-02-09"
  },
  {
    "id": "c016",
    "slug": "reinforcement-learning-foundations",
    "title": "Reinforcement Learning Foundations",
    "category": "Foundations",
    "level": "Advanced",
    "price": 139,
    "rating": 4.6,
    "duration_hours": 18,
    "students": 2200,
    "short": "MDPs, value functions, policy gradients, and exploration.",
    "description": "Implement RL agents and understand convergence and stability issues.",
    "tags": ["RL", "policy gradients"],
    "prerequisites": ["Calculus", "Probability"],
    "release": "2025-05-12",
    "updated": "2026-02-06"
  },
  {
    "id": "c017",
    "slug": "time-series-deep-learning",
    "title": "Deep Learning for Time Series",
    "category": "Foundations",
    "level": "Intermediate",
    "price": 119,
    "rating": 4.5,
    "duration_hours": 14,
    "students": 1750,
    "short": "Forecasting with CNNs, RNNs, and transformers.",
    "description": "Architectures and evaluation techniques for temporal data.",
    "tags": ["time series", "forecasting"],
    "prerequisites": ["Python"],
    "release": "2025-06-01",
    "updated": "2026-02-04"
  },
  {
    "id": "c018",
    "slug": "practical-regularization-nlp",
    "title": "Practical Regularization for NLP",
    "category": "NLP",
    "level": "Intermediate",
    "price": 109,
    "rating": 4.4,
    "duration_hours": 12,
    "students": 1300,
    "short": "Dropout, label smoothing, and adversarial training for text.",
    "description": "Regularization techniques applied to transformer-based NLP systems.",
    "tags": ["regularization", "NLP", "transformers"],
    "prerequisites": ["Optimization"],
    "release": "2025-07-10",
    "updated": "2026-02-02"
  },
  {
    "id": "c019",
    "slug": "scaling-laws",
    "title": "Scaling Laws in Deep Learning",
    "category": "Foundations",
    "level": "Advanced",
    "price": 129,
    "rating": 4.7,
    "duration_hours": 12,
    "students": 1100,
    "short": "Empirical scaling laws and compute-optimal training.",
    "description": "Study parameter count, dataset size, and compute trade-offs.",
    "tags": ["scaling", "compute"],
    "prerequisites": ["Probability", "Optimization"],
    "release": "2025-08-22",
    "updated": "2026-02-01"
  },
  {
    "id": "c020",
    "slug": "model-compression",
    "title": "Model Compression and Quantization",
    "category": "Production",
    "level": "Advanced",
    "price": 139,
    "rating": 4.5,
    "duration_hours": 14,
    "students": 1600,
    "short": "Pruning, distillation, and quantization for efficient inference.",
    "description": "Make models smaller and faster without losing accuracy.",
    "tags": ["quantization", "distillation", "pruning"],
    "prerequisites": ["Optimization"],
    "release": "2025-09-14",
    "updated": "2026-02-07"
  },
  {
    "id": "c021",
    "slug": "testing-ml-systems",
    "title": "Testing ML Systems",
    "category": "Production",
    "level": "Intermediate",
    "price": 109,
    "rating": 4.3,
    "duration_hours": 10,
    "students": 1200,
    "short": "Data tests, unit tests for models, and monitoring.",
    "description": "Reliability practices for machine learning systems in production.",
    "tags": ["testing", "production", "monitoring"],
    "prerequisites": ["Python"],
    "release": "2025-10-05",
    "updated": "2026-02-10"
  },
  {
    "id": "c022",
    "slug": "transfer-learning",
    "title": "Transfer Learning Essentials",
    "category": "Foundations",
    "level": "Intermediate",
    "price": 99,
    "rating": 4.6,
    "duration_hours": 10,
    "students": 2600,
    "short": "Fine-tune pretrained models effectively.",
    "description": "Strategies for adapting models with limited labeled data.",
    "tags": ["transfer learning", "fine-tuning"],
    "prerequisites": ["Python"],
    "release": "2025-10-30",
    "updated": "2026-02-03"
  }
]