Dl-Foundations on Reinforcement Learning Curriculum

Dl-Foundations on Reinforcement Learning Curriculum https://codefrydev.in/Reinforcement/tags/dl-foundations/ Recent content in Dl-Foundations on Reinforcement Learning Curriculum Reinforcement Learning Curriculum https://codefrydev.in/Reinforcement/og-default.png https://codefrydev.in/Reinforcement/og-default.png Hugo en-us Fri, 20 Mar 2026 00:00:00 +0000 Biological Inspiration: From Brain Neurons to Artificial Neurons https://codefrydev.in/Reinforcement/dl-foundations/biological-inspiration/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/biological-inspiration/ How the biological neuron — dendrites, soma, axon — maps onto the artificial neuron with inputs, weights, bias, and activation. The Perceptron: Learning from Mistakes https://codefrydev.in/Reinforcement/dl-foundations/perceptron/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/perceptron/ The perceptron learning rule, training on AND and OR gates, and why XOR exposes the fundamental limitation of single-layer networks. Activation Functions: Adding Non-Linearity https://codefrydev.in/Reinforcement/dl-foundations/activation-functions/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/activation-functions/ ReLU, sigmoid, tanh, and softmax — what they compute, when to use each, and why non-linearity is essential for deep networks. Multi-Layer Perceptrons: Stacking Layers to Break Linearity https://codefrydev.in/Reinforcement/dl-foundations/mlp/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/mlp/ MLP architecture, parameter counting, and how stacking non-linear layers allows networks to solve XOR and approximate any function. Forward Propagation: Computing the Network Output https://codefrydev.in/Reinforcement/dl-foundations/forward-propagation/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/forward-propagation/ Layer-by-layer forward pass through an MLP — computing pre-activations, applying activations, and understanding intermediate representations. Checkpoint: DL Foundations Mid-Point https://codefrydev.in/Reinforcement/assessment/checkpoint-dl-mid/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/assessment/checkpoint-dl-mid/ 5 questions after completing the first 6 DL Foundations pages. Check your understanding before continuing. Loss Functions: Measuring How Wrong the Network Is https://codefrydev.in/Reinforcement/dl-foundations/loss-functions-dl/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/loss-functions-dl/ MSE for regression, cross-entropy for classification, and the TD error loss in DQN — how loss functions guide neural network training. Backpropagation: Teaching Networks by Propagating Errors https://codefrydev.in/Reinforcement/dl-foundations/backpropagation/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/backpropagation/ The chain rule applied backwards through a neural network — computing gradients for every weight and verifying them with numerical finite differences. Phase 5 Assessment: Deep Learning Foundations https://codefrydev.in/Reinforcement/assessment/phase-5-dl/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/assessment/phase-5-dl/ 12 questions covering neural networks, backpropagation, training loops, and CNNs. Pass: 9/12. Optimizers: SGD, Momentum, and Adam https://codefrydev.in/Reinforcement/dl-foundations/optimizers/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/optimizers/ Understand SGD, Momentum, and Adam optimizers from scratch. Implement and compare them in NumPy. The Training Loop https://codefrydev.in/Reinforcement/dl-foundations/training-loop/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/training-loop/ Build a full training loop in NumPy: batches, epochs, forward pass, backprop, and weight updates. Regularization and Overfitting https://codefrydev.in/Reinforcement/dl-foundations/regularization/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/regularization/ Understand overfitting and apply L2 regularization and dropout to prevent it in NumPy. CNN Basics: Convolutions and Pooling https://codefrydev.in/Reinforcement/dl-foundations/cnn-basics/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/cnn-basics/ Learn convolution and pooling from scratch in NumPy. See how Atari DQN uses CNNs to process raw pixels. PyTorch: Building Neural Networks with nn.Module https://codefrydev.in/Reinforcement/dl-foundations/pytorch-nn-practice/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/pytorch-nn-practice/ Bridge NumPy implementations to PyTorch. Build QNetwork and PolicyNetwork with nn.Module for RL. DL Mini-Project: Digits Classifier in NumPy https://codefrydev.in/Reinforcement/dl-foundations/dl-mini-project/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/dl-mini-project/ Build a 2-layer MLP to classify handwritten digits using only NumPy. Full pipeline: data, init, training, evaluation. DL Foundations Drills https://codefrydev.in/Reinforcement/dl-foundations/drills/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/drills/ 15 drill problems covering neural networks, forward pass, backpropagation, optimizers, and training. DL Foundations Review & Bridge to RL https://codefrydev.in/Reinforcement/dl-foundations/review-and-bridge/ Fri, 20 Mar 2026 00:00:00 +0000 https://codefrydev.in/Reinforcement/dl-foundations/review-and-bridge/ Review deep learning and see why RL needs neural networks — the bridge to DQN and policy gradients.