Removed details around benchmarking (ended up in its own chapter)

efficient_ai.qmd

@@ -65,7 +65,7 @@ Explanation: This section offers an in-depth exploration of different AI models
   - INT8
   - Lower bit widths
 
-## Benchmarking and Evaluation of AI Models
+## Evaluating Models
 
 Explanation: This part of the chapter emphasizes the importance of evaluating the efficiency of AI models using appropriate metrics and benchmarks. This process is vital to ensuring the effectiveness of the approaches discussed earlier and seamlessly connects with case studies where these benchmarks can be seen in a real-world context.
 
@@ -78,28 +78,6 @@ Explanation: This part of the chapter emphasizes the importance of evaluating th
 - Comparative Analysis of AI Models
 - EEMBC, MLPerf Tiny, Edge
 
-## Caveat on Efficiency Metrics
-
-Explanation: This section emphasizes the diverse aspects that constitute "efficiency" in machine learning systems. It aims to guide readers in identifying the crucial metrics that matter, depending on the specific use case, underscoring the importance of considering these metrics early in the ML workflow.
-
-- Multi-faceted nature of efficiency in ML systems
-  - Beyond accuracy: various critical metrics
-  - Latency as a pivotal component 
-- Importance of low latency in real-time applications
-  - The specific application dictates acceptable latency
-- Power efficiency in embedded systems
-  - Strategies for extending battery life
-  - Role of specialized hardware 
-- Considerations for cost-efficient deployments
-  - Balancing hardware costs and model accuracy 
-  - Balancing accuracy, latency, and costs 
-- Tailoring efficiency to the product
-  - Comparison: automotive, mobile, smart home applications
-  - Distinct constraints necessitate diverse efficiency approaches
-- Early integration of efficiency metrics in ML workflow
-  - Influence on architecture, hardware, and algorithm selection
-  - Proactive consideration of efficiency metrics
-
 ## Emerging Directions
 
 - Automated model search