Link slides in chapters

contents/ai_for_good/ai_for_good.qmd

@@ -30,6 +30,7 @@ By aligning AI progress with human values, goals, and ethics, the ultimate goal
 
 :::
 
+
 ## Introduction
 
 To give ourselves a framework around which to think about AI for social good, we will be following the UN Sustainable Development Goals (SDGs). The UN SDGs are a collection of 17 global goals, shown in @fig-sdg, adopted by the United Nations in 2015 as part of the 2030 Agenda for Sustainable Development. The SDGs address global challenges related to poverty, inequality, climate change, environmental degradation, prosperity, and peace and justice.
@@ -220,7 +221,10 @@ If cultivated responsibly, TinyML could democratize opportunity and accelerate p
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [TinyML for Social Impact.](https://docs.google.com/presentation/d/1gkA6pAPUjPWND9ODgnfhCVzbwVYXdrkTpXsJdZ7hJHY/edit#slide=id.ge94401e7d6_0_81)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/benchmarking/benchmarking.qmd

@@ -14,6 +14,7 @@ Benchmarking is a critical part of developing and deploying machine learning sys
 
 This chapter will provide an overview of popular ML benchmarks, best practices for benchmarking, and how to use benchmarks to improve model development and system performance. It aims to provide developers with the right tools and knowledge to effectively benchmark and optimize their systems, especially for TinyML systems.
 
+
 ::: {.callout-tip}
 
 ## Learning Objectives
@@ -36,6 +37,7 @@ This chapter will provide an overview of popular ML benchmarks, best practices f
 
 :::
 
+
 ## Introduction {#sec-benchmarking-ai}
 
 Benchmarking provides the essential measurements needed to drive progress in machine learning and to truly understand system performance. As the physicist Lord Kelvin famously said, "To measure is to know." Benchmarks give us the ability to know the capabilities of different models, software, and hardware quantitatively. They allow ML developers to measure the inference time, memory usage, power consumption, and other metrics that characterize a system. Moreover, benchmarks create standardized processes for measurement, enabling fair comparisons across different solutions.
@@ -789,7 +791,12 @@ Benchmarking is a continuously evolving topic. The article [The Olympics of AI:
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Why is benchmarking important?](https://docs.google.com/presentation/d/17udz3gxeYF3r3X1r4ePwu1I9H8ljb53W3ktFSmuDlGs/edit?usp=drive_link&resourcekey=0-Espn0a0x81kl2txL_jIWjw)
+
+* [Embedded inference benchmarking.](https://docs.google.com/presentation/d/18PI_0xmcW1xwwfcjmj25PikqBM_92vQfOXFV4hah-6I/edit?resourcekey=0-KO3HQcDAsR--jgbKd5cp4w#slide=id.g94db9f9f78_0_2)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/data_engineering/data_engineering.qmd

@@ -12,6 +12,7 @@ Resources: [Slides](#sec-data-engineering-resource), [Labs](#sec-data-engineerin
 
 Data is the lifeblood of AI systems. Without good data, even the most advanced machine learning algorithms will fail. In this section, we will dive into the intricacies of building high-quality datasets to fuel our AI models. Data engineering encompasses the processes of collecting, storing, processing, and managing data for training machine learning models.
 
+
 ::: {.callout-tip}
 
 ## Learning Objectives
@@ -32,6 +33,7 @@ Data is the lifeblood of AI systems. Without good data, even the most advanced m
 
 :::
 
+
 ## Introduction
 
 Dataset creators face complex privacy and representation challenges when building high-quality training data, especially for sensitive domains like healthcare. Legally, creators may need to remove direct identifiers like names and ages. Even without legal obligations, removing such information can help build user trust. However, excessive anonymization can compromise dataset utility. Techniques like differential privacy$^{1}$, aggregation, and reducing detail provide alternatives to balance privacy and utility, but have downsides. Creators must strike a thoughtful balance based on use case.
@@ -436,7 +438,20 @@ Data is the fundamental building block of AI systems. Without quality data, even
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Data engineering overview.](https://docs.google.com/presentation/d/1nuNFjB99ccE6hqFeAmRRbhoEoSjBgJXGr9u6cvwnXgM/edit#slide=id.p19)
+
+* [Feature engineering.](https://docs.google.com/presentation/d/1otnrLjtBOGmrT-FBzAGajRwXJTC65OQCpGCxjxCzn_k/edit#slide=id.p1)
+
+* [Data Standards: Speech Commands.](https://docs.google.com/presentation/d/1qDoHc7yzZ2lEha9NTMZ07Ls4tkIz-1f7kUYRlvjzsI4/edit?usp=drive_link&resourcekey=0-ol4Oqk_y706P_zIB5mbu7Q)
+
+* [Crowdsourcing Data for the Long Tail.](https://docs.google.com/presentation/d/1d3KUit64L-4dXecCNBpikCxx7VO0xIJ13r9v1Ad22S4/edit#slide=id.ga4ca29c69e_0_179)
+
+* [Reusing and Adapting Existing Datasets.](https://docs.google.com/presentation/d/1mHecDoCYHQD9nWSRYCrXXG0IOp9wYQk-fbxhoNIsGMY/edit#slide=id.ga4ca29c69e_0_206)
+
+* [Responsible Data Collection.](https://docs.google.com/presentation/d/1vcmuhLVNFT2asKSCSGh_Ix9ht0mJZxMii8MufEMQhFA/edit?resourcekey=0-_pYLcW5aF3p3Bvud0PPQNg#slide=id.ga4ca29c69e_0_195)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/dl_primer/dl_primer.qmd

@@ -26,6 +26,7 @@ This section offers a brief introduction to deep learning, starting with an over
 
 :::
 
+
 ## Introduction
 
 ### Definition and Importance
@@ -238,7 +239,24 @@ Now would be an excellent time to try some deep learning models:
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Past, Present, and Future of ML.](https://docs.google.com/presentation/d/16ensKAKBG8DOUHF4f5thTJklVGTadxjm3kPkdoPyabI/edit#slide=id.g94db9f9f78_0_2)
+
+* [Thinking About Loss.](https://docs.google.com/presentation/d/1X92JqVkUY7k6yJXQcT2u83dpdrx5UzGFAJkkDMDfKe0/edit#slide=id.g94db9f9f78_0_2)
+
+* [Minimizing Loss.](https://docs.google.com/presentation/d/1x3xbZHo4VtaZgoXfueCbOGGXuWRYj0nOsKwAAoGsrD0/edit#slide=id.g94db9f9f78_0_2)
+
+* [First Neural Network.](https://docs.google.com/presentation/d/1zQwhTwF_plXBPQLxluahpzoQg-VdMyJbctaJxSUncag/edit?usp=drive_link)
+
+* [Understanding Neurons.](https://docs.google.com/presentation/d/1jXCAC6IT5f9XFKZbfhJ4p2D5URVTYqgAnkcQR4ALhSk/edit?usp=drive_link&resourcekey=0-K228bxVdwO2w3kr0daV2cw)
+
+* [Intro to CLassification.](https://docs.google.com/presentation/d/1VtWV9LAVLJ0uAkhFMbDJFjsUH6IvBDnPde4lR1cD2mo/edit?usp=drive_link)
+
+* [Training, Validation, and Test Data.](https://docs.google.com/presentation/d/1G56D0-qG9YWnzQQeje9LMpcLSotMgBCiMyfj53yz7lY/edit?usp=drive_link)
+
+* [Intro to Convolutions.](https://docs.google.com/presentation/d/1hQDabWqaKUWRb60Cze-MhAyeUUVyNgyTUMBpLnqhtvc/edit?resourcekey=0-uHZoNwsbjeY3EIMD3fYAfg#slide=id.g94db9f9f78_0_2)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/efficient_ai/efficient_ai.qmd

@@ -188,7 +188,11 @@ Moreover, efficient AI expands beyond technological optimization but also encomp
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Model Evaluation.](https://docs.google.com/presentation/d/1jdBnIxgNovG3b8frTl3DwqiIOw_K4jvp3kyv2GoKfYQ/edit?usp=drive_link&resourcekey=0-PN8sYpltO1nP_xePynJn9w)
+
+* [Continuous Evaluation Challenges for TinyML.](https://docs.google.com/presentation/d/1OuhwH5feIwPivEU6pTDyR3QMs7AFstHLiF_LB8T5qYQ/edit?usp=drive_link&resourcekey=0-DZxIuVBUbJawuFh0AO-Pvw)
 :::
 
 :::{.callout-exercise collapse="false"}

contents/embedded_ml/embedded_ml.qmd

@@ -28,6 +28,7 @@ Before delving into the intricacies of TinyML, it's crucial to grasp the distinc
 
 :::
 
+
 ## Introduction
 
 ML is rapidly evolving, with new paradigms emerging that are reshaping how these algorithms are developed, trained, and deployed. In particular, the area of embedded machine learning is experiencing significant innovation, driven by the proliferation of smart sensors, edge devices, and microcontrollers. This chapter explores the landscape of embedded machine learning, covering the key approaches of Cloud ML, Edge ML, and TinyML (@fig-cloud-edge-tinyml-comparison).
@@ -271,7 +272,12 @@ The embedded ML landscape is in a state of rapid evolution, poised to enable int
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Embedded ML Software.](https://docs.google.com/presentation/d/17wgAfoF24Rcx7uPrbau0c8FyzXIUWbe48qGGBOXXT-g/edit?resourcekey=0-Uv29DvmF7gYzKdOoRtn0vw#slide=id.g94db9f9f78_0_8)
+
+* [Embedded Inference.](https://docs.google.com/presentation/d/1FOUQ9dbe3l_qTa2AnroSbOz0ykuCz5cbTNO77tvFxEs/edit?usp=drive_link)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/embedded_sys/embedded_sys.qmd

@@ -36,6 +36,7 @@ As we journey further into this chapter, we will demystify the intricate yet cap
 
 :::
 
+
 ## Basics and Components
 
 ### Definition and Characteristics
@@ -389,7 +390,20 @@ As we gaze into the future, it's clear that the realm of embedded systems stands
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Embedded Systems Overview.](https://docs.google.com/presentation/d/1Lgrn7bddHYxyrOmk0JfSVmEBimRePqI7WSliUKRPK9E/edit?resourcekey=0-c5JvfDeqHIdV9A5RMAMAyw#slide=id.g94db9f9f78_0_8)
+
+* [Embedded Computer Hardware.](https://docs.google.com/presentation/d/1hDCFcOrZ08kZPhY4DA3gVikGUo47HwNyvqNrLW-t-Tg/edit?resourcekey=0-J6ix5AYvZMGbFFOa7ae4Hw#slide=id.g94db9f9f78_0_8)
+
+* [Embedded I/O.](https://docs.google.com/presentation/d/1rnWh9XC6iCKSx_hQd4xq2iIDlpc-GkBQw_GjzlP5mQc/edit#slide=id.g94db9f9f78_0_8)
+
+* [Embedded systems software.](https://docs.google.com/presentation/d/1TApZn9xxPWCRY-D-soJ8YOSsfysnccR5UjOyspzeTuU/edit?resourcekey=0-BRWIyCKPLNQFnIfG0fJJ9A#slide=id.g94db9f9f78_0_8)
+
+* [Embedded ML software.](https://docs.google.com/presentation/d/17wgAfoF24Rcx7uPrbau0c8FyzXIUWbe48qGGBOXXT-g/edit?resourcekey=0-Uv29DvmF7gYzKdOoRtn0vw#slide=id.g94db9f9f78_0_8)
+
+* [Embedded Inference.](https://docs.google.com/presentation/d/1FOUQ9dbe3l_qTa2AnroSbOz0ykuCz5cbTNO77tvFxEs/edit?usp=drive_link)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/frameworks/frameworks.qmd

@@ -14,6 +14,7 @@ In this chapter, we explore the landscape of AI frameworks that serve as the fou
 
 Furthermore, we investigate the specialization of frameworks tailored to specific needs, the emergence of frameworks specifically designed for embedded AI, and the criteria for selecting the most suitable framework for your project. This exploration will be rounded off by a glimpse into the future trends that are expected to shape the landscape of ML frameworks in the coming years.
 
+
 ::: {.callout-tip}
 
 ## Learning Objectives
@@ -34,6 +35,7 @@ Furthermore, we investigate the specialization of frameworks tailored to specifi
 
 :::
 
+
 ## Introduction
 
 Machine learning frameworks provide the tools and infrastructure to efficiently build, train, and deploy machine learning models. In this chapter, we will explore the evolution and key capabilities of major frameworks like [TensorFlow (TF)](https://www.tensorflow.org/), [PyTorch](https://pytorch.org/), and specialized frameworks for embedded devices. We will dive into the components like computational graphs, optimization algorithms, hardware acceleration, and more that enable developers to quickly construct performant models. Understanding these frameworks is essential to leverage the power of deep learning across the spectrum from cloud to edge devices.
@@ -709,7 +711,28 @@ Now it is time to explore a TensorFlow Lite for Microcontrollers model:
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Why do we need frameworks?](https://docs.google.com/presentation/d/1zbnsihiO68oIUE04TVJEcDQ_Kyec4mhdQkIG6xoR0DY/edit#slide=id.p1)
+
+* [Frameworks overview.](https://docs.google.com/presentation/d/1Ruibe1cvo0LhOM4GgFinR_z9IlJgZ7EX3snj8LriV-8/edit)
+
+* [Embedded systems software.](https://docs.google.com/presentation/d/1-hpejUcj4PJ6Sm8dncBm6ngUwYsBevj9jmdonfy0f8g/edit#slide=id.p1)
+
+* [Inference engines: TF vs. TFLite.](https://docs.google.com/presentation/d/12IlNZx75Z-NRK2rAO4xs5qmD7lU0h8eMibkpWPvZwHY/edit#slide=id.p1)
+
+* [TF flavors: TF vs. TFLite vs. TFLite Micro.](https://docs.google.com/presentation/d/1Gt-mhBZueCUXq1_I7qFTY8s6udDHw0ncbkQ3ZsaXCjA/edit#slide=id.p1)
+
+* TFLite Micro:
+    * [TFLite Micro Big Picture.](https://docs.google.com/presentation/d/1XdwcZS0pz6kyuk6Vx90kE11hwUMAtS1cMoFQHZAxS20/edit?usp=drive_link)
+
+    * [TFLite Micro Interpreter.](https://docs.google.com/presentation/d/10llaugp6EroGekFzB1pAH1OJ1dpJ4d7yxKglK1BsqlI/edit?usp=drive_link&resourcekey=0-C6_PHSaI6u4x0Mv2KxWKbg)
+
+    * [TFLite Micro Model Format.](https://docs.google.com/presentation/d/123kdwjRXvbukyaOBvdp0PJpIs2JSxQ7GoDjB8y0FgIE/edit?usp=drive_link)
+
+    * [TFLite Micro Memory Allocation.](https://docs.google.com/presentation/d/1_sHuWa3DDTCB9mBzKA4ElPWaUFA8oOelqHCBOHmsvC4/edit?usp=drive_link)
+
+    * [TFLite Micro NN Operations.](https://docs.google.com/presentation/d/1ZwLOLvYbKodNmyuKKGb_gD83NskrvNmnFC0rvGugJlY/edit?usp=drive_link)
 :::
 
 :::{.callout-exercise collapse="false"}

contents/ondevice_learning/ondevice_learning.qmd

@@ -28,6 +28,7 @@ On-device Learning represents a significant innovation for embedded and edge IoT
 
 :::
 
+
 ## Introduction
 
 On-device Learning refers to the process of training ML models directly on the device where they are deployed, as opposed to traditional methods where models are trained on powerful servers and then deployed to devices. This method is particularly relevant to TinyML, where ML systems are integrated into tiny, resource-constrained devices.
@@ -658,7 +659,25 @@ In conclusion, on-device learning stands at the forefront of TinyML, promising a
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [Intro to TensorFlow Lite (TFLite).](https://docs.google.com/presentation/d/19nF6CATRBqQWGBBv4uO4RzWpAwwuhmBAv8AQdBkkAVY/edit#slide=id.g94db9f9f78_0_2)
+
+* [TFLite Optimization and Quantization.](https://docs.google.com/presentation/d/1JwP46J6eLFUebNy2vKDvPzExe20DuTL95Nw8ubCxNPg/edit#slide=id.g94db9f9f78_0_2)
+
+* [TFLite Quantization-Aware Training.](https://docs.google.com/presentation/d/1eSOyAOu8Vg_VfIHZ9gWRVjWnmFTOcZ4FavaNMc4reHQ/edit#slide=id.p1)
+
+* [Transfer Learning: with Visual Wake Words exaple.](https://docs.google.com/presentation/d/1kVev1WwXG2MrpEMmRbiPjTBwQ6CSCE_K84SUlSbuUPM/edit#slide=id.ga654406365_0_127)
+
+* Continuous Monitoring:
+    * [Continuous Evaluation Challenges for TinyML.](https://docs.google.com/presentation/d/1OuhwH5feIwPivEU6pTDyR3QMs7AFstHLiF_LB8T5qYQ/edit?usp=drive_link&resourcekey=0-DZxIuVBUbJawuFh0AO-Pvw)
+
+    * [Federated Learning Challenges.](https://docs.google.com/presentation/d/1Q8M76smakrt5kTqggoPW8WFTrP0zIrV-cWj_BEfPxIA/edit?resourcekey=0-mPx0WwZOEVkHndVhr_MzMQ#slide=id.g94db9f9f78_0_2)
+
+    * [Continuous Monitoring with Federated ML.](https://docs.google.com/presentation/d/1dHqWjKflisdLhX43jjOUmZCyM0tNhXTVgcch-Bcp-uo/edit?usp=drive_link&resourcekey=0-AuuCxz6QKc-t3lXMPeX1Sg)
+
+    * [Continuous Monitoring Impact on MLOps.](https://docs.google.com/presentation/d/1D7qI7aLGnoUV7x3s5Dqa44CsJTQdDO5xtID5MBM0GxI/edit?usp=drive_link&resourcekey=0-g7SB2RDsdGt01tPCI7VeUQ)
+
 :::
 
 :::{.callout-exercise collapse="false"}

contents/ops/ops.qmd

@@ -32,6 +32,7 @@ This chapter explores the practices and architectures needed to effectively deve
 
 :::
 
+
 ## Introduction
 
 Machine Learning Operations (MLOps), is a systematic approach that combines machine learning (ML), data science, and software engineering to automate the end-to-end ML lifecycle. This includes everything from data preparation and model training to deployment and maintenance. MLOps ensures that ML models are developed, deployed, and maintained efficiently and effectively.
@@ -842,7 +843,46 @@ While embedded MLOps faces impediments, emerging tools like Edge Impulse and les
 :::{.callout-slide collapse="false"}
 # Slides
 
-Coming soon.
+**Teaching material pertaining to this chapter are curated in a slides format and linked below:**
+
+* [MLOps, DevOps, and AIOps.](https://docs.google.com/presentation/d/1vsC8WpmvVRgMTpzTltAhEGzcVohMkatMZBqm3-P8TUY/edit?usp=drive_link)
+
+* [MLOps overview.](https://docs.google.com/presentation/d/1tG7YfW-FwC5Up3gLk-DrvOkpKmkMPO6y2k-t7FJgK3s/edit#slide=id.p1)
+
+* [Tiny MLOps.](https://docs.google.com/presentation/d/1Sa27wZmKokVyKwmLLM2p_HHAam-sXKVPxzxqv-0y2V8/edit)
+
+* [MLOps: a use case.](https://docs.google.com/presentation/d/1qhBZvtHe5jya6TAAmZKlK2oowQUfBwhIOcfk1fpoGq4/edit?resourcekey=0-xKK09GAhYbOK6dB_RrSvkw#slide=id.ged8f947d63_0_0)
+
+* [MLOps: Key Activities and Lifecycle.](https://docs.google.com/presentation/d/1awWKlEYyYcHp5HR5MXomg0v6uevtvFV76HjesxrN_9g/edit#slide=id.geb6aec3278_0_0)
+
+* [ML Lifecycle.](https://docs.google.com/presentation/d/1FW8Q1Yj5g_jbArFANfncbLQj36uV2vfV8pjoqaD6gjM/edit#slide=id.g94db9f9f78_0_2)
+
+* [Scaling TinyML: Challenges and Opportunities.](https://docs.google.com/presentation/d/1VxwhVztoTk3eG04FD9fFNpj2lVrVjYYPJi3jBz0O_mo/edit?resourcekey=0-bV7CCIPr7SxZf2p61oB_CA#slide=id.g94db9f9f78_0_2)
+
+* Training Operationalizatios:
+    * [Training Ops: CI/CD trigger.](https://docs.google.com/presentation/d/1YyRY6lOzdC7NjutJSvl_VXYu29qwHKqx0y98zAUCJCU/edit?resourcekey=0-PTh1FxqkQyhOO0bKKHBldQ#slide=id.g94db9f9f78_0_2)
+
+    * [Continuous Integration.](https://docs.google.com/presentation/d/1poGgYTH44X0dVGwG9FGIyVwot4EET_jJOt-4kgcQawo/edit?usp=drive_link)
+
+    * [Continuous Deployment.](https://docs.google.com/presentation/d/1nxbIluROAOl5cN6Ug4Dm-mHh1Fwm5aEng_S5iLfiCqo/edit?usp=drive_link&resourcekey=0-xFOl8i7ea2vNtiilXz8CaQ)
+
+    * [Production Deployment.](https://docs.google.com/presentation/d/1m8KkCZRnbJCCTWsmcwMt9EJhYLoaVG_Wm7zUE2bQkZI/edit?usp=drive_link)
+
+    * [Production Deployment: Online Experimentation.](https://docs.google.com/presentation/d/1elFEK61X5Kc-5UV_4AEtRvCT7l1TqTdABmJV8uAYykY/edit?usp=drive_link)
+
+    * [Training Ops Impact on MLOps.](https://docs.google.com/presentation/d/1-6QL2rq0ahGVz8BL1M1BT0lR-HDxsHady9lGTN93wLc/edit?usp=drive_link&resourcekey=0-sRqqoa7pX9IkDDSwe2MLyw)
+
+* Model Deployment:
+    * [Scaling ML Into Production Deployment.](https://docs.google.com/presentation/d/12sf-PvSxDIlCQCXULWy4jLY_2fIq-jpRojRsmeMGq6k/edit?resourcekey=0-knPSQ5h4ffhgeV6CXvwlSg#slide=id.gf209f12c63_0_314)
+
+    * [Containers for Scaling ML Deployment.](https://docs.google.com/presentation/d/1YXE4cAWMwL79Vqr_8TJi-LsQD9GFdiyBqY--HcoBpKg/edit?usp=drive_link&resourcekey=0-yajtiQTx2SdJ6BCVG0Bfng)
+
+    * [Challenges for Scaling TinyML Deployment: Part 1.](https://docs.google.com/presentation/d/1mw5FFERf5r-q8R7iyNf6kx2MMcwNOTBd5WwFOj8Zs20/edit?resourcekey=0-u80KeJio3iIWco00crGD9g#slide=id.gdc4defd718_0_0)
+
+    * [Challenges for Scaling TinyML Deploymnet: Part 2.](https://docs.google.com/presentation/d/1NB63wTHoEPGSn--KqFu1vjHx3Ild9AOhpBbflJP-k7I/edit?usp=drive_link&resourcekey=0-MsEi1Lba2dpl0G-bzakHJQ)
+
+    * [Model Deployment Impact on MLOps.](https://docs.google.com/presentation/d/1A0pfm55s03dFbYKKFRV-x7pRCm_2-VpoIM0O9kW0TAA/edit?usp=drive_link&resourcekey=0--O2AFFmVzAmz5KO0mJeVHA)
+
 :::
 
 :::{.callout-exercise collapse="false"}