[ { "id": "nv-101", "title": "Neural Networks Foundations", "category": "Foundations", "level": "Beginner", "durationHours": 18, "price": 99, "rating": 4.8, "lessons": 24, "shortDescription": "Build intuition about perceptrons, activation functions, loss, and gradient descent with friendly visuals.", "details": "Learn core building blocks of neural networks: tensors, forward passes, activation choices, initialization, and optimization with SGD and Adam. Practice with clean notebooks and reflective checkpoints.", "skills": ["Python", "NumPy", "Autograd", "Optimization"], "prerequisites": ["Basic Python"], "tags": ["beginner", "math-light", "SGD"] }, { "id": "nv-102", "title": "Practical PyTorch", "category": "Foundations", "level": "Beginner", "durationHours": 16, "price": 109, "rating": 4.7, "lessons": 20, "shortDescription": "Hands-on PyTorch for tensors, datasets, training loops, and debugging.", "details": "Set up robust datasets, build models, manage training loops and metrics, and learn to read stack traces calmly. Includes tips for reproducibility and sanity checks.", "skills": ["PyTorch", "Training Loops", "Metrics"], "prerequisites": ["Neural Networks Foundations"], "tags": ["pytorch", "reproducibility"] }, { "id": "nv-103", "title": "Optimization in Deep Learning", "category": "Foundations", "level": "Intermediate", "durationHours": 14, "price": 119, "rating": 4.6, "lessons": 18, "shortDescription": "From SGD to AdamW and schedulers with intuition-first explanations.", "details": "Understand loss surfaces, vanishing/exploding gradients, adaptive methods, weight decay, warmup, cosine schedules, and gradient clipping with practical experiments.", "skills": ["AdamW", "Schedulers", "Regularization"], "prerequisites": ["Practical PyTorch"], "tags": ["optimization", "regularization"] }, { "id": "nv-201", "title": "Convolutional Networks for Vision", "category": "Computer Vision", "level": "Intermediate", "durationHours": 20, "price": 139, "rating": 4.7, "lessons": 22, "shortDescription": "CNNs for image classification and feature extraction with transfer learning.", "details": "Build and fine-tune CNNs, use augmentations, and apply transfer learning from ResNet and EfficientNet on small datasets. Includes model evaluation and explainability sections.", "skills": ["CNN", "Transfer Learning", "Augmentation"], "prerequisites": ["Practical PyTorch"], "tags": ["vision", "classification"] }, { "id": "nv-202", "title": "Object Detection and Segmentation", "category": "Computer Vision", "level": "Advanced", "durationHours": 24, "price": 159, "rating": 4.6, "lessons": 24, "shortDescription": "Train detectors (Faster R-CNN, YOLO) and U-Net for segmentation.", "details": "Learn anchor boxes, NMS, mAP, segmentation losses, and build a lightweight inference API. Includes dataset labeling best practices and error analysis.", "skills": ["YOLO", "Faster R-CNN", "U-Net"], "prerequisites": ["Convolutional Networks for Vision"], "tags": ["detection", "segmentation"] }, { "id": "nv-203", "title": "Vision Transformers", "category": "Computer Vision", "level": "Advanced", "durationHours": 18, "price": 159, "rating": 4.5, "lessons": 20, "shortDescription": "Self-attention for images with ViT and hybrid CNN-Transformer models.", "details": "Tokenization of patches, positional encodings, attention maps, pretraining vs. fine-tuning, and performance tips for small datasets.", "skills": ["Transformers", "Attention", "Fine-tuning"], "prerequisites": ["Convolutional Networks for Vision"], "tags": ["transformers", "vit"] }, { "id": "nv-301", "title": "Natural Language Processing with RNNs and LSTMs", "category": "Natural Language", "level": "Intermediate", "durationHours": 18, "price": 129, "rating": 4.6, "lessons": 21, "shortDescription": "Sequence modeling fundamentals with RNNs, LSTMs, and embeddings.", "details": "Build tokenizers, embeddings, and sequence models. Cover masking, teacher forcing, and evaluation with perplexity and F1 for classification tasks.", "skills": ["Tokenization", "RNN", "LSTM"], "prerequisites": ["Practical PyTorch"], "tags": ["nlp", "sequence"] }, { "id": "nv-302", "title": "Transformers for NLP", "category": "Natural Language", "level": "Advanced", "durationHours": 20, "price": 159, "rating": 4.7, "lessons": 22, "shortDescription": "Attention, encoders/decoders, and fine-tuning BERT-like models.", "details": "Implement attention, layer norms, and train or fine-tune BERT/RoBERTa for classification and QA. Learn prompt-based fine-tuning and evaluation pitfalls.", "skills": ["Attention", "BERT", "Fine-tuning"], "prerequisites": ["Natural Language Processing with RNNs and LSTMs"], "tags": ["nlp", "transformers"] }, { "id": "nv-303", "title": "Responsible NLP", "category": "Natural Language", "level": "Intermediate", "durationHours": 14, "price": 119, "rating": 4.5, "lessons": 16, "shortDescription": "Bias, fairness, and safety practices for language models.", "details": "Measure bias, apply debiasing, handle toxicity filters, and document datasets with transparency. Includes ethics case studies and mitigation checklists.", "skills": ["Fairness", "Bias Mitigation", "Safety"], "prerequisites": ["Transformers for NLP"], "tags": ["ethics", "fairness"] }, { "id": "nv-401", "title": "Generative Models: VAEs and GANs", "category": "Generative", "level": "Advanced", "durationHours": 22, "price": 159, "rating": 4.6, "lessons": 24, "shortDescription": "Build and evaluate VAEs and GANs with stability strategies.", "details": "Variational inference, KL annealing, adversarial losses, instability diagnosis, and FID metrics. Includes careful tips for training dynamics.", "skills": ["VAE", "GAN", "Stability"], "prerequisites": ["Optimization in Deep Learning"], "tags": ["generative", "vae", "gan"] }, { "id": "nv-402", "title": "Diffusion Models", "category": "Generative", "level": "Advanced", "durationHours": 24, "price": 169, "rating": 4.5, "lessons": 22, "shortDescription": "Denoising diffusion with U-Net backbones and schedulers.", "details": "Forward/reverse processes, noise schedules, classifier-free guidance, and efficient sampling strategies with small compute budgets.", "skills": ["Diffusion", "Sampling", "Schedulers"], "prerequisites": ["Generative Models: VAEs and GANs"], "tags": ["diffusion", "sampling"] }, { "id": "nv-403", "title": "Prompt Engineering with Transformers", "category": "Generative", "level": "Intermediate", "durationHours": 12, "price": 109, "rating": 4.4, "lessons": 14, "shortDescription": "System prompts, few-shot patterns, and evaluation without overfitting.", "details": "Design robust prompts, evaluate with rubrics, and avoid leakage. Includes content moderation strategies and human-in-the-loop reviews.", "skills": ["Prompting", "Evaluation", "Guardrails"], "prerequisites": ["Transformers for NLP"], "tags": ["prompting", "evaluation"] }, { "id": "nv-501", "title": "MLOps Basics", "category": "MLOps & Deployment", "level": "Intermediate", "durationHours": 16, "price": 129, "rating": 4.6, "lessons": 18, "shortDescription": "From experiments to reproducible training and simple CI.", "details": "Track experiments, manage data versions, containerize training, and build a minimal CI to test notebooks and pipelines.", "skills": ["DVC", "Docker", "CI"], "prerequisites": ["Practical PyTorch"], "tags": ["mlops", "reproducibility"] }, { "id": "nv-502", "title": "Deploying Models with FastAPI", "category": "MLOps & Deployment", "level": "Intermediate", "durationHours": 14, "price": 129, "rating": 4.7, "lessons": 16, "shortDescription": "Serve models with FastAPI and lightweight inference patterns.", "details": "Package models, write prediction endpoints, handle batching, validation, and simple auth. Includes latency profiling and scaling options.", "skills": ["FastAPI", "Inference", "Profiling"], "prerequisites": ["MLOps Basics"], "tags": ["deployment", "api"] }, { "id": "nv-503", "title": "Monitoring and Observability", "category": "MLOps & Deployment", "level": "Advanced", "durationHours": 16, "price": 139, "rating": 4.5, "lessons": 18, "shortDescription": "Data drift, model performance, and human feedback loops.", "details": "Set up telemetry, define SLOs, detect drift, and build alerts. Add human feedback channels and escalation paths for safety.", "skills": ["Observability", "Data Drift", "SLOs"], "prerequisites": ["MLOps Basics"], "tags": ["monitoring", "drift"] }, { "id": "nv-601", "title": "Tabular Deep Learning", "category": "Applied", "level": "Intermediate", "durationHours": 14, "price": 109, "rating": 4.5, "lessons": 16, "shortDescription": "Entity embeddings, feature crosses, and robust evaluation.", "details": "Work with messy business data, handle categoricals with embeddings, and evaluate with repeated CV to avoid leakage.", "skills": ["Embeddings", "Evaluation", "Tabular"], "prerequisites": ["Practical PyTorch"], "tags": ["tabular", "embeddings"] }, { "id": "nv-602", "title": "Time Series Forecasting", "category": "Applied", "level": "Intermediate", "durationHours": 16, "price": 119, "rating": 4.5, "lessons": 18, "shortDescription": "Temporal convolutions, seq2seq baselines, and careful backtesting.", "details": "Build robust backtests, compare classical baselines to deep models, and manage covariates and holidays cleanly.", "skills": ["Backtesting", "Temporal CNN", "Seq2Seq"], "prerequisites": ["Practical PyTorch"], "tags": ["time series", "forecasting"] }, { "id": "nv-603", "title": "Recommender Systems", "category": "Applied", "level": "Advanced", "durationHours": 18, "price": 139, "rating": 4.4, "lessons": 18, "shortDescription": "Collaborative filtering, implicit feedback, and ranking metrics.", "details": "Matrix factorization, implicit methods, negative sampling, and A/B testing basics for recommendation pipelines.", "skills": ["Recommendations", "Ranking", "A/B Testing"], "prerequisites": ["Tabular Deep Learning"], "tags": ["recommendations", "ranking"] }, { "id": "nv-701", "title": "Math for Deep Learning (Gentle)", "category": "Foundations", "level": "Beginner", "durationHours": 20, "price": 99, "rating": 4.7, "lessons": 22, "shortDescription": "A calm tour of vectors, matrices, derivatives, and probabilities for DL.", "details": "Learn the essentials with carefully paced visuals and practice problems that focus on intuition before proofs.", "skills": ["Linear Algebra", "Calculus", "Probability"], "prerequisites": ["High school algebra"], "tags": ["math", "beginner"] }, { "id": "nv-702", "title": "Data Cleaning for ML", "category": "Foundations", "level": "Beginner", "durationHours": 12, "price": 89, "rating": 4.6, "lessons": 14, "shortDescription": "From raw files to tidy datasets with careful checks and documentation.", "details": "Detect leakage, handle missing values, normalize features, and keep a reproducible audit trail.", "skills": ["Pandas", "Validation", "Docs"], "prerequisites": ["Basic Python"], "tags": ["data", "cleaning"] }, { "id": "nv-703", "title": "Explainability in Deep Learning", "category": "Foundations", "level": "Intermediate", "durationHours": 14, "price": 119, "rating": 4.5, "lessons": 16, "shortDescription": "Saliency, SHAP, and counterfactuals with sanity checks.", "details": "Use feature attributions responsibly, validate explanations, and communicate uncertainty to stakeholders.", "skills": ["Explainability", "SHAP", "Reporting"], "prerequisites": ["Neural Networks Foundations"], "tags": ["explainability", "ethics"] }, { "id": "nv-801", "title": "Graph Neural Networks", "category": "Applied", "level": "Advanced", "durationHours": 18, "price": 149, "rating": 4.4, "lessons": 18, "shortDescription": "Message passing, GCN, and GraphSAGE on real-world graphs.", "details": "Implement GNN layers, sampling strategies, and evaluate robustness with corrupted edges.", "skills": ["GNN", "GraphSAGE", "Sampling"], "prerequisites": ["Optimization in Deep Learning"], "tags": ["graph", "gnn"] }, { "id": "nv-802", "title": "Reinforcement Learning Essentials", "category": "Applied", "level": "Advanced", "durationHours": 20, "price": 149, "rating": 4.3, "lessons": 20, "shortDescription": "Value-based and policy-based RL with careful reward design.", "details": "DQN, PPO, and advantage methods with debugging strategies and safety constraints for exploration.", "skills": ["RL", "PPO", "DQN"], "prerequisites": ["Optimization in Deep Learning"], "tags": ["rl", "control"] } ]