Update README.md

README.md

@@ -48,7 +48,7 @@ Despite lacking global error gradients and relying on raw un-smoothed SGD, the m
 
 ## Notes for the future
 Accuracy of 74% achieved after 50 epochs; training loss still descending, suggesting higher accuracy is achievable with further training
-Future work: larger model, bigger batch sizes, or both — all feasible on consumer-grade hardware given the minimal VRAM footprint. (100-200mb during Training On T4 GPU hardware)
+Future work: larger model, bigger batch sizes, or both — all feasible on consumer-grade hardware given the minimal VRAM footprint.
 ## Conclusion & The "Efficient-Hardware" Theory
 This experiment successfully proves that a deep neural network can learn at scale (1.3M parameters) without ever constructing a massive, memory-hogging backpropagation graph. 
 By relying on local Goodness evaluation and Predictive Coding errors, this architecture theoretically slashes the VRAM requirements of large-scale AI training, posing an experimental alternative to the hardware-heavy standard backpropagation paradigm.