feat: Update environment.yml with PyTorch and add installation guide

- environment.yml: Added PyTorch with CUDA 12.1, PyG (torch-geometric),
  and TensorBoard for neural network training
- INSTALL_INSTRUCTIONS.md: Step-by-step guide for installing Miniconda
  and setting up the Atomizer environment

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

INSTALL_INSTRUCTIONS.md

@@ -0,0 +1,63 @@
+# Atomizer Installation Guide
+
+## Step 1: Install Miniconda (Recommended)
+
+1. Download Miniconda from: https://docs.conda.io/en/latest/miniconda.html
+   - Choose: **Miniconda3 Windows 64-bit**
+
+2. Run the installer:
+   - Check "Add Miniconda3 to my PATH environment variable"
+   - Check "Register Miniconda3 as my default Python"
+
+3. Restart your terminal/VSCode after installation
+
+## Step 2: Create Atomizer Environment
+
+Open **Anaconda Prompt** (or any terminal after restart) and run:
+
+```bash
+cd C:\Users\Antoine\Atomizer
+conda env create -f environment.yml
+conda activate atomizer
+```
+
+## Step 3: Install PyTorch with GPU Support (Optional but Recommended)
+
+If you have an NVIDIA GPU:
+
+```bash
+conda activate atomizer
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
+pip install torch-geometric
+```
+
+## Step 4: Verify Installation
+
+```bash
+conda activate atomizer
+python -c "import torch; import optuna; import pyNastran; print('All imports OK!')"
+python -c "import torch; print(f'CUDA available: {torch.cuda.is_available()}')"
+```
+
+## Step 5: Train Neural Network
+
+```bash
+conda activate atomizer
+cd C:\Users\Antoine\Atomizer\atomizer-field
+python train_parametric.py --train_dir ../atomizer_field_training_data/bracket_stiffness_optimization_atomizerfield --epochs 100 --output_dir runs/bracket_model
+```
+
+## Quick Commands Reference
+
+```bash
+# Activate environment (do this every time you open a new terminal)
+conda activate atomizer
+
+# Train neural network
+cd C:\Users\Antoine\Atomizer\atomizer-field
+python train_parametric.py --train_dir ../atomizer_field_training_data/bracket_stiffness_optimization_atomizerfield --epochs 100
+
+# Run optimization with neural acceleration
+cd C:\Users\Antoine\Atomizer\studies\bracket_stiffness_optimization_atomizerfield
+python run_optimization.py --run --trials 100 --enable-nn
+```

environment.yml

@@ -14,6 +14,8 @@
 name: atomizer
 channels:
   - pytorch
+  - nvidia
+  - pyg
   - conda-forge
   - defaults
 
@@ -41,7 +43,19 @@ dependencies:
   # FEA/Nastran Parsing
   # ============================================================================
   - h5py>=3.0.0
-  - pip
+
+  # ============================================================================
+  # Neural Network / AtomizerField
+  # ============================================================================
+  # PyTorch with CUDA support
+  - pytorch>=2.0.0
+  - pytorch-cuda=12.1
+
+  # PyTorch Geometric for Graph Neural Networks
+  - pyg>=2.3.0
+
+  # TensorBoard for training visualization
+  - tensorboard>=2.13.0
 
   # ============================================================================
   # Web Framework (Dashboard/API)
@@ -67,6 +81,7 @@ dependencies:
   # ============================================================================
   # pip-only packages (not available in conda)
   # ============================================================================
+  - pip
   - pip:
     # Nastran file parser (numpy<2 constraint is handled above)
     - pyNastran>=1.4.0,<1.5.0
@@ -79,11 +94,10 @@ dependencies:
 # ============================================================================
 #
 # 1. Verify installation:
-#    python -c "import optuna; import pyNastran; print('All imports OK')"
+#    python -c "import optuna; import pyNastran; import torch; print('All imports OK')"
 #
-# 2. For NX integration, ensure NX Python stubs are accessible:
+# 2. Check GPU:
+#    python -c "import torch; print(f'CUDA: {torch.cuda.is_available()}')"
+#
+# 3. For NX integration, ensure NX Python stubs are accessible:
 #    See config.py for NX_PYTHON_STUBS path
-#
-# 3. For AtomizerField neural surrogates, install PyTorch and torch-geometric separately:
-#    conda install pytorch pytorch-cuda=12.1 -c pytorch -c nvidia
-#    pip install torch-geometric tensorboard