Merge pull request #278 from harvard-edge/276-a-minor-syntax-issue-in…

…-the-formatting

Fixed formatting issue

contents/dl_primer/dl_primer.qmd

@@ -213,21 +213,21 @@ To briefly highlight the differences, @tbl-mlvsdl illustrates the contrasting ch
 
 #### Data Availability and Volume
 
-* **Amount of Data:** Traditional machine learning algorithms, such as decision trees or Naive Bayes, are often more suitable when data availability is limited. They offer robust predictions even with smaller datasets. This is particularly true in medical diagnostics for disease prediction and customer segmentation in marketing.
+**Amount of Data:** Traditional machine learning algorithms, such as decision trees or Naive Bayes, are often more suitable when data availability is limited. They offer robust predictions even with smaller datasets. This is particularly true in medical diagnostics for disease prediction and customer segmentation in marketing.
 
-* **Data Diversity and Quality:** Traditional machine learning algorithms often work well with structured data (the input to the model is a set of features, ideally independent of each other) but may require significant preprocessing effort (i.e., feature engineering). On the other hand, deep learning takes the approach of automatically performing feature engineering as part of the model architecture. This approach enables the construction of end-to-end models capable of directly mapping from unstructured input data (such as text, audio, and images) to the desired output without relying on simplistic heuristics that have limited effectiveness. However, this results in larger models demanding more data and computational resources. In noisy data, the necessity for larger datasets is further emphasized when utilizing Deep Learning.
+**Data Diversity and Quality:** Traditional machine learning algorithms often work well with structured data (the input to the model is a set of features, ideally independent of each other) but may require significant preprocessing effort (i.e., feature engineering). On the other hand, deep learning takes the approach of automatically performing feature engineering as part of the model architecture. This approach enables the construction of end-to-end models capable of directly mapping from unstructured input data (such as text, audio, and images) to the desired output without relying on simplistic heuristics that have limited effectiveness. However, this results in larger models demanding more data and computational resources. In noisy data, the necessity for larger datasets is further emphasized when utilizing Deep Learning.
 
 #### Complexity of the Problem
 
-* **Problem Granularity:** Problems that are simple to moderately complex, which may involve linear or polynomial relationships between variables, often find a better fit with traditional machine learning methods.
+**Problem Granularity:** Problems that are simple to moderately complex, which may involve linear or polynomial relationships between variables, often find a better fit with traditional machine learning methods.
 
-* **Hierarchical Feature Representation:** Deep learning models are excellent in tasks that require hierarchical feature representation, such as image and speech recognition. However, not all problems require this complexity, and traditional machine learning algorithms may sometimes offer simpler and equally effective solutions.
+**Hierarchical Feature Representation:** Deep learning models are excellent in tasks that require hierarchical feature representation, such as image and speech recognition. However, not all problems require this complexity, and traditional machine learning algorithms may sometimes offer simpler and equally effective solutions.
 
 #### Hardware and Computational Resources
 
-* **Resource Constraints:** The availability of computational resources often influences the choice between traditional ML and deep learning. The former is generally less resource-intensive and thus preferable in environments with hardware limitations or budget constraints.
+**Resource Constraints:** The availability of computational resources often influences the choice between traditional ML and deep learning. The former is generally less resource-intensive and thus preferable in environments with hardware limitations or budget constraints.
 
-* **Scalability and Speed:** Traditional machine learning algorithms, like support vector machines (SVM), often allow for faster training times and easier scalability, which is particularly beneficial in projects with tight timelines and growing data volumes.
+**Scalability and Speed:** Traditional machine learning algorithms, like support vector machines (SVM), often allow for faster training times and easier scalability, which is particularly beneficial in projects with tight timelines and growing data volumes.
 
 #### Regulatory Compliance
 
@@ -241,9 +241,7 @@ Understanding the decision-making process is easier with traditional machine lea
 
 Given the constraints of embedded AI systems, understanding the differences between traditional ML techniques and deep learning becomes essential. Both avenues offer unique advantages, and their distinct characteristics often dictate the choice of one over the other in different scenarios.
 
-Despite this, deep learning has steadily outperformed traditional machine learning methods in several key areas due to abundant data, computational advancements, and proven effectiveness in complex tasks.
-
-Here are some specific reasons why we focus on deep learning in this text:
+Despite this, deep learning has steadily outperformed traditional machine learning methods in several key areas due to abundant data, computational advancements, and proven effectiveness in complex tasks. Here are some specific reasons why we focus on deep learning:
 
 1. **Superior Performance in Complex Tasks:** Deep learning models, particularly deep neural networks, excel in tasks where the relationships between data points are incredibly intricate. Tasks like image and speech recognition, language translation, and playing complex games like Go and Chess have seen significant advancements primarily through deep learning algorithms.