Skip to content

Commit

Permalink
Push dev branch build
Browse files Browse the repository at this point in the history
  • Loading branch information
@Naeemkh
Naeemkh committed May 21, 2024
1 parent ad3bc9f commit 9373600
Show file tree
Hide file tree
Showing 4 changed files with 26 additions and 26 deletions.
4 changes: 2 additions & 2 deletions docs/contents/contributors.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -575,10 +575,10 @@ <h1 class="title">Contributors</h1>
</tr>
<tr>
<td align="center" valign="top" width="20%">
<a href="https://github.com/mpstewart1"><img src="https://avatars.githubusercontent.com/mpstewart1?s=100" width="100px;" alt="Matthew Stewart"><br><sub><b>Matthew Stewart</b></sub></a><br>
<a href="https://github.com/JaredP94"><img src="https://avatars.githubusercontent.com/JaredP94?s=100" width="100px;" alt="Jared Ping"><br><sub><b>Jared Ping</b></sub></a><br>
</td>
<td align="center" valign="top" width="20%">
<a href="https://github.com/JaredP94"><img src="https://avatars.githubusercontent.com/JaredP94?s=100" width="100px;" alt="Jared Ping"><br><sub><b>Jared Ping</b></sub></a><br>
<a href="https://github.com/mpstewart1"><img src="https://avatars.githubusercontent.com/mpstewart1?s=100" width="100px;" alt="Matthew Stewart"><br><sub><b>Matthew Stewart</b></sub></a><br>
</td>
<td align="center" valign="top" width="20%">
<a href="https://github.com/eliasab16"><img src="https://avatars.githubusercontent.com/eliasab16?s=100" width="100px;" alt="eliasab16"><br><sub><b>eliasab16</b></sub></a><br>
Expand Down
8 changes: 4 additions & 4 deletions docs/contents/frameworks/frameworks.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1430,7 +1430,7 @@ <h3 data-number="6.8.3" class="anchored" data-anchor-id="library"><span class="h
<section id="choosing-the-right-framework" class="level2" data-number="6.9">
<h2 data-number="6.9" class="anchored" data-anchor-id="choosing-the-right-framework"><span class="header-section-number">6.9</span> Choosing the Right Framework</h2>
<p>Choosing the right machine learning framework for a given application requires carefully evaluating models, hardware, and software considerations. By analyzing these three aspects—models, hardware, and software—ML engineers can select the optimal framework and customize it as needed for efficient and performant on-device ML applications. The goal is to balance model complexity, hardware limitations, and software integration to design a tailored ML pipeline for embedded and edge devices.</p>
<div id="fig-tf-comparison" class="quarto-figure quarto-figure-center quarto-float anchored" data-caption="TensorFlow Framework Comparison - General" data-align="center">
<div id="fig-tf-comparison" class="quarto-figure quarto-figure-center quarto-float anchored" data-align="center" data-caption="TensorFlow Framework Comparison - General">
<figure class="quarto-float quarto-float-fig figure">
<div aria-describedby="fig-tf-comparison-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
<img src="images/png/image4.png" style="width:100.0%" data-align="center" data-caption="TensorFlow Framework Comparison - General" class="figure-img">
Expand All @@ -1446,7 +1446,7 @@ <h3 data-number="6.9.1" class="anchored" data-anchor-id="model"><span class="hea
</section>
<section id="software" class="level3" data-number="6.9.2">
<h3 data-number="6.9.2" class="anchored" data-anchor-id="software"><span class="header-section-number">6.9.2</span> Software</h3>
<div id="fig-tf-sw-comparison" class="quarto-figure quarto-figure-center quarto-float anchored" data-caption="TensorFlow Framework Comparison - Model" data-align="center">
<div id="fig-tf-sw-comparison" class="quarto-figure quarto-figure-center quarto-float anchored" data-align="center" data-caption="TensorFlow Framework Comparison - Model">
<figure class="quarto-float quarto-float-fig figure">
<div aria-describedby="fig-tf-sw-comparison-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
<img src="images/png/image5.png" style="width:100.0%" data-align="center" data-caption="TensorFlow Framework Comparison - Model" class="figure-img">
Expand All @@ -1460,7 +1460,7 @@ <h3 data-number="6.9.2" class="anchored" data-anchor-id="software"><span class="
</section>
<section id="hardware" class="level3" data-number="6.9.3">
<h3 data-number="6.9.3" class="anchored" data-anchor-id="hardware"><span class="header-section-number">6.9.3</span> Hardware</h3>
<div id="fig-tf-hw-comparison" class="quarto-figure quarto-figure-center quarto-float anchored" data-caption="TensorFlow Framework Comparison - Hardware" data-align="center">
<div id="fig-tf-hw-comparison" class="quarto-figure quarto-figure-center quarto-float anchored" data-align="center" data-caption="TensorFlow Framework Comparison - Hardware">
<figure class="quarto-float quarto-float-fig figure">
<div aria-describedby="fig-tf-hw-comparison-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
<img src="images/png/image3.png" style="width:100.0%" data-align="center" data-caption="TensorFlow Framework Comparison - Hardware" class="figure-img">
Expand Down Expand Up @@ -1507,7 +1507,7 @@ <h2 data-number="6.10" class="anchored" data-anchor-id="future-trends-in-ml-fram
<section id="decomposition" class="level3" data-number="6.10.1">
<h3 data-number="6.10.1" class="anchored" data-anchor-id="decomposition"><span class="header-section-number">6.10.1</span> Decomposition</h3>
<p>Currently, the ML system stack consists of four abstractions as shown in <a href="#fig-mlsys-stack" class="quarto-xref">Figure&nbsp;<span>6.10</span></a>, namely (1) computational graphs, (2) tensor programs, (3) libraries and runtimes, and (4) hardware primitives.</p>
<div id="fig-mlsys-stack" class="quarto-figure quarto-figure-center quarto-float anchored" data-caption="Four Abstractions in Current ML System Stack" data-align="center">
<div id="fig-mlsys-stack" class="quarto-figure quarto-figure-center quarto-float anchored" data-align="center" data-caption="Four Abstractions in Current ML System Stack">
<figure class="quarto-float quarto-float-fig figure">
<div aria-describedby="fig-mlsys-stack-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
<img src="images/png/image8.png" class="img-fluid figure-img" data-align="center" data-caption="Four Abstractions in Current ML System Stack">
Expand Down
32 changes: 16 additions & 16 deletions docs/contents/robust_ai/robust_ai.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1317,7 +1317,7 @@ <h4 class="anchored" data-anchor-id="impact-on-ml-systems-3">Impact on ML System
<img src="./images/png/graffiti.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-graffiti-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.21: Graffiti on a stop sign tricked a self-driving car into thinking it was a 45 mph speed limit sign (Source: <a href="https://arxiv.org/abs/1707.08945">Eykholt</a>)
Figure&nbsp;17.21: Graffiti on a stop sign tricked a self-driving car into thinking it was a 45 mph speed limit sign (Credit: <a href="https://arxiv.org/abs/1707.08945">Eykholt</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1364,7 +1364,7 @@ <h4 class="anchored" data-anchor-id="definition-and-characteristics-4">Definitio
<img src="./images/png/poisoning_example.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-poisoning-example-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.22: NightShade’s poisoning effects on Stable Diffusion (Source: <a href="https://telefonicatech.com/en/blog/attacks-on-artificial-intelligence-iii-data-poisoning">TOMÉ</a>)
Figure&nbsp;17.22: NightShade’s poisoning effects on Stable Diffusion (Credit: <a href="https://telefonicatech.com/en/blog/attacks-on-artificial-intelligence-iii-data-poisoning">TOMÉ</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1409,7 +1409,7 @@ <h4 class="anchored" data-anchor-id="mechanisms-of-data-poisoning">Mechanisms of
<img src="./images/png/distribution_shift_example.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-distribution-shift-example-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.23: Garbage In – Garbage Out (Source: <a href="https://informationmatters.net/data-poisoning-ai/">Information Matters</a>)
Figure&nbsp;17.23: Garbage In – Garbage Out (Credit: <a href="https://informationmatters.net/data-poisoning-ai/">Information Matters</a>)
</figcaption>
</figure>
</div>
Expand All @@ -1424,7 +1424,7 @@ <h4 class="anchored" data-anchor-id="mechanisms-of-data-poisoning">Mechanisms of
<img src="./images/png/poisoning_attack_example.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-poisoning-attack-example-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.24: Data Poisoning Attack (Source: <a href="https://www.researchgate.net/publication/366883200_A_Detailed_Survey_on_Federated_Learning_Attacks_and_Defenses">Sikandar</a>)
Figure&nbsp;17.24: Data Poisoning Attack (Credit: <a href="https://www.researchgate.net/publication/366883200_A_Detailed_Survey_on_Federated_Learning_Attacks_and_Defenses">Sikandar</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1459,7 +1459,7 @@ <h5 class="anchored" data-anchor-id="case-study-2">Case Study 2</h5>
<img src="./images/png/dirty_label_example.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-dirty-label-example-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.25: Samples of dirty-label poison data regarding mismatched text/image pairs (Source: <a href="https://arxiv.org/pdf/2310.13828">Shan</a>)
Figure&nbsp;17.25: Samples of dirty-label poison data regarding mismatched text/image pairs (Credit: <a href="https://arxiv.org/pdf/2310.13828">Shan</a>)
</figcaption>
</figure>
</div>
Expand All @@ -1474,7 +1474,7 @@ <h5 class="anchored" data-anchor-id="case-study-2">Case Study 2</h5>
<img src="images/png/image14.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-poisoning-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.26: Data poisoning (Source: <span class="citation" data-cites="shan2023prompt">Shan et al. (<a href="../../references.html#ref-shan2023prompt" role="doc-biblioref">2023</a>)</span>)
Figure&nbsp;17.26: Data poisoning (Credit: <span class="citation" data-cites="shan2023prompt">Shan et al. (<a href="../../references.html#ref-shan2023prompt" role="doc-biblioref">2023</a>)</span>)
</figcaption>
<div class="no-row-height column-margin column-container"><div id="ref-shan2023prompt" class="csl-entry" role="listitem">
Shan, Shawn, Wenxin Ding, Josephine Passananti, Haitao Zheng, and Ben Y Zhao. 2023. <span>“Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models.”</span> <em>ArXiv Preprint</em> abs/2310.13828. <a href="https://arxiv.org/abs/2310.13828">https://arxiv.org/abs/2310.13828</a>.
Expand Down Expand Up @@ -1506,7 +1506,7 @@ <h4 class="anchored" data-anchor-id="definition-and-characteristics-5">Definitio
<img src="./images/png/distribution_shift.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-distribution-shift-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.27: The curly brackets enclose the distribution shift between the environments. Here, z stands for the spurious feature, and y stands for label class (Source: <a href="https://www.researchgate.net/publication/366423741_On_the_Connection_between_Invariant_Learning_and_Adversarial_Training_for_Out-of-Distribution_Generalization">Xin</a>)
Figure&nbsp;17.27: The curly brackets enclose the distribution shift between the environments. Here, z stands for the spurious feature, and y stands for label class (Credit: <a href="https://www.researchgate.net/publication/366423741_On_the_Connection_between_Invariant_Learning_and_Adversarial_Training_for_Out-of-Distribution_Generalization">Xin</a>)
</figcaption>
</figure>
</div>
Expand All @@ -1521,7 +1521,7 @@ <h4 class="anchored" data-anchor-id="definition-and-characteristics-5">Definitio
<img src="./images/png/drift_over_time.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-drift-over-time-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.28: Concept drift refers to a change in data patterns and relationships over time (Source: <a href="https://www.evidentlyai.com/ml-in-production/concept-drift">Evidently AI</a>)
Figure&nbsp;17.28: Concept drift refers to a change in data patterns and relationships over time (Credit: <a href="https://www.evidentlyai.com/ml-in-production/concept-drift">Evidently AI</a>)
</figcaption>
</figure>
</div>
Expand All @@ -1540,7 +1540,7 @@ <h4 class="anchored" data-anchor-id="mechanisms-of-distribution-shifts">Mechanis
<img src="./images/png/temporal_evoltion.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-temporal-evoltion-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.29: Temporal evolution (Source: <a href="https://www.nannyml.com/blog/types-of-data-shift">Białek</a>)
Figure&nbsp;17.29: Temporal evolution (Credit: <a href="https://www.nannyml.com/blog/types-of-data-shift">Białek</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1615,7 +1615,7 @@ <h5 class="anchored" data-anchor-id="anomaly-detection-techniques-for-identifyin
<img src="./images/png/adversarial_attack_injection.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-adversarial-attack-injection-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.30: Malicious data injection (Source: <a href="https://www.mdpi.com/2227-7390/12/2/247">Li</a>)
Figure&nbsp;17.30: Malicious data injection (Credit: <a href="https://www.mdpi.com/2227-7390/12/2/247">Li</a>)
</figcaption>
</figure>
</div>
Expand All @@ -1627,7 +1627,7 @@ <h5 class="anchored" data-anchor-id="anomaly-detection-techniques-for-identifyin
<img src="./images/png/autoencoder.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-autoencoder-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.31: Autoencoder (Source: <a href="https://towardsdatascience.com/applied-deep-learning-part-3-autoencoders-1c083af4d798">Dertat</a>)
Figure&nbsp;17.31: Autoencoder (Credit: <a href="https://towardsdatascience.com/applied-deep-learning-part-3-autoencoders-1c083af4d798">Dertat</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1685,7 +1685,7 @@ <h5 class="anchored" data-anchor-id="mitigation-techniques-for-distribution-shif
<img src="./images/png/transfer_learning.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-transfer-learning-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.33: Transfer learning (Source: <a href="https://medium.com/modern-nlp/transfer-learning-in-nlp-f5035cc3f62f">Bhavsar</a>)
Figure&nbsp;17.33: Transfer learning (Credit: <a href="https://medium.com/modern-nlp/transfer-learning-in-nlp-f5035cc3f62f">Bhavsar</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1767,7 +1767,7 @@ <h4 class="anchored" data-anchor-id="detection-and-mitigation-2">Detection and M
<img src="./images/png/regression_testing.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-regression-testing-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.35: Automated regression testing (Source: <a href="https://u-tor.com/topic/regression-vs-integration">UTOR</a>)
Figure&nbsp;17.35: Automated regression testing (Credit: <a href="https://u-tor.com/topic/regression-vs-integration">UTOR</a>)
</figcaption>
</figure>
</div>
Expand All @@ -1785,7 +1785,7 @@ <h4 class="anchored" data-anchor-id="detection-and-mitigation-2">Detection and M
<img src="./images/png/CI_CD_procedure.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-CI-CD-procedure-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.36: Continuous Integration/Continuous Deployment (CI/CD) procedure (Source: <a href="https://www.geeksforgeeks.org/ci-cd-continuous-integration-and-continuous-delivery/">geeksforgeeks</a>)
Figure&nbsp;17.36: Continuous Integration/Continuous Deployment (CI/CD) procedure (Credit: <a href="https://www.geeksforgeeks.org/ci-cd-continuous-integration-and-continuous-delivery/">geeksforgeeks</a>)
</figcaption>
</figure>
</div>
Expand Down Expand Up @@ -1875,7 +1875,7 @@ <h4 class="anchored" data-anchor-id="methods">Methods</h4>
<img src="./images/png/image14.png" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-beam-testing-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.39: Radiation test setup for semiconductor components <span class="citation" data-cites="lee2022design">(<a href="../../references.html#ref-lee2022design" role="doc-biblioref">Lee et al. 2022</a>)</span> (Source: <a href="https://jdinstruments.net/tester-capabilities-radiation-test/">JD Instrument</a>)
Figure&nbsp;17.39: Radiation test setup for semiconductor components <span class="citation" data-cites="lee2022design">(<a href="../../references.html#ref-lee2022design" role="doc-biblioref">Lee et al. 2022</a>)</span> (Credit: <a href="https://jdinstruments.net/tester-capabilities-radiation-test/">JD Instrument</a>)
</figcaption>
<div class="no-row-height column-margin column-container"><div id="ref-lee2022design" class="csl-entry" role="listitem">
Lee, Minwoong, Namho Lee, Huijeong Gwon, Jongyeol Kim, Younggwan Hwang, and Seongik Cho. 2022. <span>“Design of Radiation-Tolerant High-Speed Signal Processing Circuit for Detecting Prompt Gamma Rays by Nuclear Explosion.”</span> <em>Electronics</em> 11 (18): 2970. <a href="https://doi.org/10.3390/electronics11182970">https://doi.org/10.3390/electronics11182970</a>.
Expand Down Expand Up @@ -1912,7 +1912,7 @@ <h5 class="anchored" data-anchor-id="limitations-1">Limitations</h5>
<img src="./images/png/mavfi.jpg" class="img-fluid figure-img">
</div>
<figcaption class="quarto-float-caption-bottom quarto-float-caption quarto-float-fig" id="fig-mavfi-caption-0ceaefa1-69ba-4598-a22c-09a6ac19f8ca">
Figure&nbsp;17.40: Comparison of techniques at layers of abstraction (Source: <a href="https://ieeexplore.ieee.org/abstract/document/10315202">MAVFI</a>)
Figure&nbsp;17.40: Comparison of techniques at layers of abstraction (Credit: <a href="https://ieeexplore.ieee.org/abstract/document/10315202">MAVFI</a>)
</figcaption>
</figure>
</div>
Expand Down
Loading

0 comments on commit 9373600

Please sign in to comment.