Update README.md

README.md

@@ -183,6 +183,25 @@ The model achieves **99.16% accuracy** on the MNIST test set, consistent with st
 ## Model Examination
 
 The model's convolutional filters learn edge detectors and stroke patterns in the first layers, which compose into digit-specific features in deeper layers. Standard CNN interpretability techniques (e.g., Grad-CAM) can be applied to visualize which regions most influence predictions.
+
+---
+
+## Environmental Impact
+
+Carbon emissions estimated using the [ML Impact Calculator](https://mlco2.github.io/impact#compute).
+
+| Factor          | Value                  |
+|-----------------|------------------------|
+| Hardware Type   | NVIDIA T4 GPU          |
+| Hours Used      | ~0.2 hrs (10 min)     |
+| Cloud Provider  | Google Colab / Local   |
+| Compute Region  | Singapore              |
+| Carbon Emitted  | ~0.01 kg CO₂eq (est.)  |
+
+---
+
+## Technical Specifications
+
 ### Model Architecture
 
 #### Convolutional Blocks
@@ -208,38 +227,6 @@ The model's convolutional filters learn edge detectors and stroke patterns in th
 | Linear   | 10     | Raw logits                          |
 
 **Total Parameters: ~3.5M** — Kaiming Normal initialization throughout.
----
-
-## Environmental Impact
-
-Carbon emissions estimated using the [ML Impact Calculator](https://mlco2.github.io/impact#compute).
-
-| Factor          | Value                  |
-|-----------------|------------------------|
-| Hardware Type   | NVIDIA T4 GPU          |
-| Hours Used      | ~0.2 hrs (10 min)     |
-| Cloud Provider  | Google Colab / Local   |
-| Compute Region  | Singapore              |
-| Carbon Emitted  | ~0.01 kg CO₂eq (est.)  |
-
----
-
-## Technical Specifications
-
-### Model Architecture
-
-| Layer         | Details                         |
-|---------------|---------------------------------|
-| Conv2D (1)    | 32 filters, 3×3 kernel, ReLU    |
-| MaxPooling    | 2×2                             |
-| Conv2D (2)    | 64 filters, 3×3 kernel, ReLU    |
-| MaxPooling    | 2×2                             |
-| Flatten       | —                               |
-| Dense         | 128 units, ReLU                 |
-| Dropout       | p = 0.5                         |
-| Output        | 10 units, Softmax               |
-
-**Total Parameters:** ~430,000
 
 ### Compute Infrastructure