index.json

[{"authors":null,"categories":null,"content":"I am a fourth-year Computer Science Ph.D. Student at the Center for Language and Speech Processing at Johns Hopkins University, supervised by Kevin Duh and Kenton Murray.\nPreviously, I was at Yale University studying math and computer science, and working with Dragomir Radev at the Yale LILY Lab. During Summer 2023, I interned with Maha Elbayad at Meta AI Research in Menlo Park, CA.\n","date":1730160000,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1730160000,"objectID":"9088776efefd8852df7793b9deaafb43","permalink":"","publishdate":"0001-01-01T00:00:00Z","relpermalink":"","section":"authors","summary":"I am a fourth-year Computer Science Ph.D. Student at the Center for Language and Speech Processing at Johns Hopkins University, supervised by Kevin Duh and Kenton Murray.\nPreviously, I was at Yale University studying math and computer science, and working with Dragomir Radev at the Yale LILY Lab.","tags":null,"title":"Neha Verma","type":"authors"},{"authors":null,"categories":null,"content":"👋 Welcome to the Academic Template The Wowchemy Academic Resumé Template for Hugo empowers you to create your job-winning online resumé and showcase your academic publications.\nCheck out the latest demo of what you’ll get in less than 10 minutes, or view the showcase.\nWowchemy makes it easy to create a beautiful website for free. Edit your site in Markdown, Jupyter, or RStudio (via Blogdown), generate it with Hugo, and deploy with GitHub or Netlify. Customize anything on your site with widgets, themes, and language packs.\n👉 Get Started 📚 View the documentation 💬 Chat with the Wowchemy community or Hugo community 🐦 Twitter: @wowchemy @GeorgeCushen #MadeWithWowchemy 💡 Request a feature or report a bug for Wowchemy ⬆️ Updating Wowchemy? View the Update Guide and Release Notes Crowd-funded open-source software To help us develop this template and software sustainably under the MIT license, we ask all individuals and businesses that use it to help support its ongoing maintenance and development via sponsorship.\n❤️ Click here to unlock rewards with sponsorship You’re looking at a Wowchemy widget This homepage section is an example of adding elements to the Blank widget.\nBackgrounds can be applied to any section. Here, the background option is set give a color gradient.\nTo remove this section, delete content/home/demo.md.\nGet inspired Check out the Markdown files which power the Academic Demo, or view the showcase.\n","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"1d1825344e8f4b25c2137e0a9c8b655f","permalink":"https://nverma1.github.io/home-unused/demo/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/demo/","section":"home-unused","summary":"👋 Welcome to the Academic Template The Wowchemy Academic Resumé Template for Hugo empowers you to create your job-winning online resumé and showcase your academic publications.\nCheck out the latest demo of what you’ll get in less than 10 minutes, or view the showcase.","tags":null,"title":"Academic Template","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"4a7e3501655fed0a4b0ce814e15ff2c9","permalink":"https://nverma1.github.io/home-unused/skills/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/skills/","section":"home-unused","summary":"","tags":null,"title":"Skills","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"d6682c06ff2f3dd0fc28f7e2c0702d07","permalink":"https://nverma1.github.io/home-unused/experience/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/experience/","section":"home-unused","summary":"","tags":null,"title":"Experience","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"9e909a8894fd21a2eff4b3e43238d81e","permalink":"https://nverma1.github.io/home-unused/accomplishments/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/accomplishments/","section":"home-unused","summary":"","tags":null,"title":"Accomplish\u0026shy;ments","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"0e643989bdefe366f2b5fddf949a36b6","permalink":"https://nverma1.github.io/home-unused/posts/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/posts/","section":"home-unused","summary":"","tags":null,"title":"Recent Posts","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"89201c04ad04664a30c3fb9ba7b170aa","permalink":"https://nverma1.github.io/home-unused/projects/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/projects/","section":"home-unused","summary":"","tags":null,"title":"Projects","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"d927b251d3da15a737d1f66fb88d4504","permalink":"https://nverma1.github.io/home-unused/talks/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/talks/","section":"home-unused","summary":"","tags":null,"title":"Recent \u0026 Upcoming Talks","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"28f54f6e819207239a6024bbaa9d78de","permalink":"https://nverma1.github.io/home-unused/featured/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/featured/","section":"home-unused","summary":"","tags":null,"title":"Featured Publications","type":"home-unused"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"657179738bed56748434d6ae76e8a647","permalink":"https://nverma1.github.io/home-unused/tags/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/home-unused/tags/","section":"home-unused","summary":"","tags":null,"title":"Popular Topics","type":"home-unused"},{"authors":[],"categories":null,"content":" Click on the Slides button above to view the built-in slides feature. Slides can be added in a few ways:\nCreate slides using Wowchemy’s Slides feature and link using slides parameter in the front matter of the talk file Upload an existing slide deck to static/ and link using url_slides parameter in the front matter of the talk file Embed your slides (e.g. Google Slides) or presentation video on this page using shortcodes. Further event details, including page elements such as image galleries, can be added to the body of this page.\n","date":1906549200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1906549200,"objectID":"a8edef490afe42206247b6ac05657af0","permalink":"https://nverma1.github.io/talk/example-talk/","publishdate":"2017-01-01T00:00:00Z","relpermalink":"/talk/example-talk/","section":"event","summary":"An example talk using Wowchemy's Markdown slides feature.","tags":[],"title":"Example Talk","type":"event"},{"authors":["Neha Verma","Kenton Murray","Kevin Duh"],"categories":null,"content":"\r","date":1730160000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1730160000,"objectID":"8df8dd64600bd7488a0fa6496a63c258","permalink":"https://nverma1.github.io/publication/merge_ffs/","publishdate":"2024-10-29T00:00:00Z","relpermalink":"/publication/merge_ffs/","section":"publication","summary":"\r","tags":[],"title":"Merging Feed Forward Sublayers for Compressed Transformers","type":"publication"},{"authors":["Neha Verma"],"categories":null,"content":" Table of Contents 1. Overview 2. Inputs and Outputs 3. Formula 1. Overview CKA (Centered Kernel Alignment) is a state-of-the-art tool for measuring the similarity of neural network representations. After reading the original paper, I wanted more intuition about how the CKA formulae capture similarity, so I spent some time breaking it down. This post is a summary of my understanding of CKA, and the derivations I worked out.\n2. Inputs and Outputs To run CKA, we must have 2 matrices of activations (aka representations) from the same neural network, or different neural networks.\nLet’s call these matrices $X$ and $Y$. Let $X \\in \\mathbb{R}^{n \\times d_1}$ and $Y \\in \\mathbb{R}^{n \\times d_2}$, where $n$ is the number of samples and $d_i$ is the dimensionality of the representations. $d_1$ and $d_2$ can be different, but $n$ must be the same for both matrices, and must be the same corresponding examples. This means CKA lets us compare the similarity of representations that come from layers of differing widths. We also assume that these matrices have been centered.\n3. Formula One formula for (linear) CKA is given by: $$\\text{CKA}(X,Y) = \\frac{\\lVert Y^TX \\rVert_F^2}{\\lVert X^TX \\rVert_F \\lVert Y^TY \\rVert_F}$$\nBreaking down the Numerator Let’s first look at the numerator of the formula: $$\\lVert Y^TX \\rVert_F^2$$ In Section 3 of Similarity of Neural Network Representations Revisited, we are shown a way to link from dot products between examples to dot products between features: $$ \\frac{\\lVert Y^TX \\rVert_F^2}{\\lVert X^TX \\rVert_F \\lVert Y^TY \\rVert_F} = \\langle \\text{vec}(XX^T), \\text{vec}(YY^T)\\rangle$$ This is the key insight of CKA, where a computation comparing the multivariate features between the two matrices can actually translate to computing the similarity between examples, and then comparing the resulting similarity structures. Although we can expand the reduced formulation, it is much more helpful to expand the formuation as follows in order to reach the intuition presented by the authors. We will work this the opposite way here, including more details to understand the intermediate steps. First, we will establish an important property of the Frobenius norm, and of the trace.\nfrobenius norm reformulation: $ \\lVert A \\rVert_F = \\sqrt{\\text{Tr}(A^TA)}$\ntrace property (cyclic property): $\\text{Tr}(ABC) = \\text{Tr}(CAB) = \\text{Tr}(BCA)$\nNow, we can rewrite the numerator of the CKA formula as follows: $$ \\begin{align*} \\lVert Y^TX \\rVert_F^2 \u0026amp;= \\left(\\sqrt{\\text{Tr}((Y^TX)^T Y^TX)}\\right)^2 \u0026amp;\u0026amp; \\text{frobenius norm}\\\\\\ \u0026amp;= Tr\\left(X^TYY^TX\\right) \u0026amp;\u0026amp; \\text{sqrt and transpose} \\\\\\ \u0026amp;= Tr\\left(XX^TYY^T\\right) \u0026amp;\u0026amp; \\text{cyclic trace} \\\\\\ \u0026amp;= \\sum_i \\left(XX^TYY^T\\right)_{ii} \u0026amp;\u0026amp; \\text{expanding trace} \\\\\\ \u0026amp;= \\sum_i \\sum_j (XX^T)_{ij} (YY^T)_{ji}\u0026amp;\u0026amp; \\text{expanding matmul} \\\\\\ \u0026amp;= \\sum_i \\sum_j (XX^T)_{ij} (YY^T)_{ij} \u0026amp;\u0026amp;\\text{gram mats symm.} \\\\\\ \u0026amp;= \\langle \\text{vec}(XX^T), \\text{vec}(YY^T)\\rangle \u0026amp;\u0026amp; \\text{dot product def.} \\end{align*} $$\nNow we have a more complete understanding of the key Equation 1 in the paper, which relates feature similarity to the dot product between similarity structures.\nConnection to the Hilbert Schmidt Independence Criterion Before formulating the connection to the Hilbert-Schmidt Independence Criterion (HSIC), we’ll first recall the definition of the cross-covariance matrix $$\\text{cov}(X,Y) = \\frac{1}{n-1}\\left(X - \\mathbb{E}(X)\\right)\\left(Y - \\mathbb{E}(Y)\\right)^T$$ Now, we will connect the trace formulation from above to the covariance matrix. Remember that we assume our data matrices are already centered $$ \\begin{align*} \\lVert \\text{cov}(X^T, Y^T)\\rVert_F^2 \u0026amp;= \\lVert \\frac{1}{n-1} X^TY \\rVert_F^2\u0026amp;\u0026amp; \\text{by def.\u0026amp;center}\\\\\\ \u0026amp;= \\frac{1}{(n-1)^2} \\lVert Y^TX \\rVert_F^2 \u0026amp;\u0026amp; \\text{scalar\u0026amp;norm} \\\\\\ \u0026amp; = \\frac{1}{(n-1)^2} \\text{Tr}\\left(XX^TYY^T\\right) \u0026amp;\u0026amp; \\text{from above} \\end{align*}$$ Now, the HSIC was originaly proposed as a test statistic for determining if variables are independent. We will now go over the empirical estimator of the HSIC, with kernels $K$ and $L$ and centering matrix $H_n = I_n - \\frac{1}{n} \\mathbb{1}\\mathbb{1}^T$ is $$ \\text{HSIC}(K,L) = \\frac{1}{(n-1)^2} \\text{Tr}(KHLH)$$ However, the HSIC is not invariant to isotropic scaling, defined as $s(X,Y) = s(\\alpha X, \\beta Y)$ for similarity index $s$. For CKA, we would like this property. Therefore, the authors propose to use a normalized version. We now share the simplifications for a linear kernel CKA, and an arbitrary kernel CKA. For the linear kernel, we have $$ \\text{HSIC}(X,Y) = \\frac{1}{(n-1)^2}\\text{Tr}(X^TXY^TY) $$ For linear CKA, we get $$ \\begin{align*} \\text{CKA}(X,Y) \u0026amp;= \\frac{\\text{HSIC}(K,L)}{\\sqrt{\\text{HSIC}(K,K)\\text{HSIC}(L,L)}} \\\\\\ \u0026amp;= \\frac{\\frac{1}{(n-1)^2} \\lVert Y^TX \\rVert_F^2}{\\sqrt{\\frac{1}{(n-1)^2} \\lVert X^TX \\rVert_F^2 \\frac{1}{(n-1)^2} \\lVert Y^TY \\rVert_F^2} }\\\\\\ \u0026amp;= \\frac{\\frac{1}{(n-1)^2} \\lVert Y^TX \\rVert_F^2}{\\frac{1}{n-1}\\cdot \\frac{1}{n-1} \\lVert X^TX \\rVert_F \\lVert Y^TY \\rVert_F} …","date":1728000000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1728000000,"objectID":"d34b8d0aa0e75bd0d5735141937502c4","permalink":"https://nverma1.github.io/post/cka_walkthrough/","publishdate":"2024-10-04T00:00:00Z","relpermalink":"/post/cka_walkthrough/","section":"post","summary":"Explaining Centered Kernel Alignment (CKA) in more detail, and working out some of the derivations from the original Kornblith et al. paper.","tags":null,"title":"Understanding CKA","type":"post"},{"authors":["Neha Verma","Maha Elbayad"],"categories":null,"content":"\r","date":1719792000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1719792000,"objectID":"7778e402cea6a5bc8ba88759284cda1f","permalink":"https://nverma1.github.io/publication/merge2024/","publishdate":"2024-07-01T00:00:00Z","relpermalink":"/publication/merge2024/","section":"publication","summary":"\r","tags":[],"title":"Merging Text Transformer Models from Different Initializations","type":"publication"},{"authors":["Neha Verma","Kenton Murray","Kevin Duh"],"categories":null,"content":"\r","date":1716422400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1716422400,"objectID":"598b65b430060416853fd5d159ce13c1","permalink":"https://nverma1.github.io/publication/rep_comb2023/","publishdate":"2024-05-23T00:00:00Z","relpermalink":"/publication/rep_comb2023/","section":"publication","summary":"\r","tags":[],"title":"Exploring Representational Disparities Between Multilingual and Bilingual Translation Models","type":"publication"},{"authors":["Elizabeth Salesky","Neha Verma","Phillip Koehn","Matt Post"],"categories":null,"content":"\r","date":1701820800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1701820800,"objectID":"c51e126ebbf2512a817479a503b9c73f","permalink":"https://nverma1.github.io/publication/liz2023/","publishdate":"2023-12-06T00:00:00Z","relpermalink":"/publication/liz2023/","section":"publication","summary":"\r","tags":[],"title":"Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer","type":"publication"},{"authors":["Amir Hussein","Cihan Xiao","Neha Verma","Thomas Thebaud","Matthew Wiesner","Sanjeev Khudanpur"],"categories":null,"content":" ","date":1689206400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1689206400,"objectID":"27d441f4d6ae4a4f6b0ef587cf689502","permalink":"https://nverma1.github.io/publication/iwslt23_dialect/","publishdate":"2023-07-13T00:00:00Z","relpermalink":"/publication/iwslt23_dialect/","section":"publication","summary":" ","tags":[],"title":"JHU IWSLT 2023 Dialect Speech Translation System Description","type":"publication"},{"authors":["Henry Li Xinyuan","Neha Verma","Bismarck Bamfo Odoom","Ujvala Pradeep","Matthew Wiesner","Sanjeev Khudanpur"],"categories":null,"content":"\r","date":1689206400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1689206400,"objectID":"dc561e9e4ef51536be41da0c725e1bf7","permalink":"https://nverma1.github.io/publication/iwslt23_multi/","publishdate":"2023-07-13T00:00:00Z","relpermalink":"/publication/iwslt23_multi/","section":"publication","summary":"\r","tags":[],"title":"JHU IWSLT 2023 Multilingual Speech Translation System Description","type":"publication"},{"authors":["Kelly Marchisio","Neha Verma","Kevin Duh","Philipp Koehn"],"categories":null,"content":" ","date":1669852800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1669852800,"objectID":"5fbecd07140457862dfef67fd8b8d750","permalink":"https://nverma1.github.io/publication/emnlp2022/","publishdate":"2022-01-01T00:00:00Z","relpermalink":"/publication/emnlp2022/","section":"publication","summary":" ","tags":[],"title":"IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces","type":"publication"},{"authors":["Irene Li","Jessica Pan","Jeremy Goldwasser","Neha Verma","Wai Pan Wong","Muhammed Yavuz Nuzumlalı","Benjamin Rosand","Yixin Li","Matthew Zhang","David Chang","R Andrew Taylor","Harlan M Krumholz","Dragomir Radev"],"categories":null,"content":" ","date":1667260800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1667260800,"objectID":"d4e884cb3b6412acf3bc3caee5299ae8","permalink":"https://nverma1.github.io/publication/ehr_review/","publishdate":"2022-11-01T00:00:00Z","relpermalink":"/publication/ehr_review/","section":"publication","summary":" ","tags":[],"title":"Neural Natural Language Processing for unstructured data in electronic health records: A review","type":"publication"},{"authors":["Neha Verma","Kenton Murray","Kevin Duh"],"categories":null,"content":" ","date":1661990400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1661990400,"objectID":"9d53582606ede62d690352122c8f6720","permalink":"https://nverma1.github.io/publication/amta2022/","publishdate":"2022-09-01T00:00:00Z","relpermalink":"/publication/amta2022/","section":"publication","summary":" ","tags":[],"title":"Strategies for Adapting Multilingual Pre-training for Domain-Specific Machine Translation","type":"publication"},{"authors":["Linyong Nan","Chiachun Hsieh","Ziming Mao","Xi Victoria Lin","Neha Verma","Rui Zhang","Wojciech Kryściński","Nick Schoelkopf","Riley Kong","Xiangru Tang","Mutethia Mutuma","Ben Rosand","Isabel Trindade","Renusree Bandaru","Jacob Cunningham","Caiming Xiong","Dragomir Radev"],"categories":null,"content":" ","date":1640995200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1640995200,"objectID":"f09c477993149653a7e197fe6c42734c","permalink":"https://nverma1.github.io/publication/tacl2022/","publishdate":"2022-01-01T00:00:00Z","relpermalink":"/publication/tacl2022/","section":"publication","summary":" ","tags":[],"title":"FeTaQA: Free-form Table Question Answering","type":"publication"},{"authors":["Linyong Nan","Dragomir Radev","Rui Zhang","Amrit Rau","Abhinand Sivaprasad","Chiachun Hsieh","Xiangru Tang","Aadit Vyas","Neha Verma","Pranav Krishna","Yangxiaokang Liu","Nadia Irwanto","Jessica Pan","Faiaz Rahman","Ahmad Zaidi","Mutethia Mutuma","Yasin Tarabar","Ankit Gupta","Tao Yu","Yi Chern Tan","Xi Victoria Lin","Caiming Xiong","Richard Socher","Nazneen Fatema Rajani"],"categories":null,"content":" ","date":1622505600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1622505600,"objectID":"36de98c19fb0c54f2a4358fa4d790bbf","permalink":"https://nverma1.github.io/publication/naacl2021/","publishdate":"2021-06-01T00:00:00Z","relpermalink":"/publication/naacl2021/","section":"publication","summary":" ","tags":[],"title":"DART: Open-Domain Structured Data Record to Text Generation","type":"publication"},{"authors":["Rui Zhang","Caitlin Westerfield","Sungrok Shim","Garrett Bingham","Alexander Fabbri","William Hu","Neha Verma","Dragomir Radev"],"categories":null,"content":" ","date":1561939200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1561939200,"objectID":"34b10369e84a59f1879af2a0c97f2b57","permalink":"https://nverma1.github.io/publication/acl2019/","publishdate":"2019-07-01T00:00:00Z","relpermalink":"/publication/acl2019/","section":"publication","summary":" ","tags":[],"title":"Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations","type":"publication"},{"authors":[],"categories":[],"content":"Create slides in Markdown with Wowchemy Wowchemy | Documentation\nFeatures Efficiently write slides in Markdown 3-in-1: Create, Present, and Publish your slides Supports speaker notes Mobile friendly slides Controls Next: Right Arrow or Space Previous: Left Arrow Start: Home Finish: End Overview: Esc Speaker notes: S Fullscreen: F Zoom: Alt + Click PDF Export Code Highlighting Inline code: variable\nCode block:\nporridge = \u0026#34;blueberry\u0026#34; if porridge == \u0026#34;blueberry\u0026#34;: print(\u0026#34;Eating...\u0026#34;) Math In-line math: $x + y = z$\nBlock math:\nFragments Make content appear incrementally\n{{% fragment %}} One {{% /fragment %}} {{% fragment %}} **Two** {{% /fragment %}} {{% fragment %}} Three {{% /fragment %}} Press Space to play!\nOne Two Three A fragment can accept two optional parameters:\nclass: use a custom style (requires definition in custom CSS) weight: sets the order in which a fragment appears Speaker Notes Add speaker notes to your presentation\n{{% speaker_note %}} - Only the speaker can read these notes - Press `S` key to view {{% /speaker_note %}} Press the S key to view the speaker notes!\nOnly the speaker can read these notes Press S key to view Themes black: Black background, white text, blue links (default) white: White background, black text, blue links league: Gray background, white text, blue links beige: Beige background, dark text, brown links sky: Blue background, thin dark text, blue links night: Black background, thick white text, orange links serif: Cappuccino background, gray text, brown links simple: White background, black text, blue links solarized: Cream-colored background, dark green text, blue links Custom Slide Customize the slide style and background\n{{\u0026lt; slide background-image=\u0026#34;/media/boards.jpg\u0026#34; \u0026gt;}} {{\u0026lt; slide background-color=\u0026#34;#0000FF\u0026#34; \u0026gt;}} {{\u0026lt; slide class=\u0026#34;my-style\u0026#34; \u0026gt;}} Custom CSS Example Let’s make headers navy colored.\nCreate assets/css/reveal_custom.css with:\n.reveal section h1, .reveal section h2, .reveal section h3 { color: navy; } Questions? Ask\nDocumentation\n","date":1549324800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1549324800,"objectID":"0e6de1a61aa83269ff13324f3167c1a9","permalink":"https://nverma1.github.io/slides/example/","publishdate":"2019-02-05T00:00:00Z","relpermalink":"/slides/example/","section":"slides","summary":"An introduction to using Wowchemy's Slides feature.","tags":[],"title":"Slides","type":"slides"},{"authors":null,"categories":null,"content":"Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum. Sed ac faucibus dolor, scelerisque sollicitudin nisi. Cras purus urna, suscipit quis sapien eu, pulvinar tempor diam. Quisque risus orci, mollis id ante sit amet, gravida egestas nisl. Sed ac tempus magna. Proin in dui enim. Donec condimentum, sem id dapibus fringilla, tellus enim condimentum arcu, nec volutpat est felis vel metus. Vestibulum sit amet erat at nulla eleifend gravida.\nNullam vel molestie justo. Curabitur vitae efficitur leo. In hac habitasse platea dictumst. Sed pulvinar mauris dui, eget varius purus congue ac. Nulla euismod, lorem vel elementum dapibus, nunc justo porta mi, sed tempus est est vel tellus. Nam et enim eleifend, laoreet sem sit amet, elementum sem. Morbi ut leo congue, maximus velit ut, finibus arcu. In et libero cursus, rutrum risus non, molestie leo. Nullam congue quam et volutpat malesuada. Sed risus tortor, pulvinar et dictum nec, sodales non mi. Phasellus lacinia commodo laoreet. Nam mollis, erat in feugiat consectetur, purus eros egestas tellus, in auctor urna odio at nibh. Mauris imperdiet nisi ac magna convallis, at rhoncus ligula cursus.\nCras aliquam rhoncus ipsum, in hendrerit nunc mattis vitae. Duis vitae efficitur metus, ac tempus leo. Cras nec fringilla lacus. Quisque sit amet risus at ipsum pharetra commodo. Sed aliquam mauris at consequat eleifend. Praesent porta, augue sed viverra bibendum, neque ante euismod ante, in vehicula justo lorem ac eros. Suspendisse augue libero, venenatis eget tincidunt ut, malesuada at lorem. Donec vitae bibendum arcu. Aenean maximus nulla non pretium iaculis. Quisque imperdiet, nulla in pulvinar aliquet, velit quam ultrices quam, sit amet fringilla leo sem vel nunc. Mauris in lacinia lacus.\nSuspendisse a tincidunt lacus. Curabitur at urna sagittis, dictum ante sit amet, euismod magna. Sed rutrum massa id tortor commodo, vitae elementum turpis tempus. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Aenean purus turpis, venenatis a ullamcorper nec, tincidunt et massa. Integer posuere quam rutrum arcu vehicula imperdiet. Mauris ullamcorper quam vitae purus congue, quis euismod magna eleifend. Vestibulum semper vel augue eget tincidunt. Fusce eget justo sodales, dapibus odio eu, ultrices lorem. Duis condimentum lorem id eros commodo, in facilisis mauris scelerisque. Morbi sed auctor leo. Nullam volutpat a lacus quis pharetra. Nulla congue rutrum magna a ornare.\nAliquam in turpis accumsan, malesuada nibh ut, hendrerit justo. Cum sociis natoque penatibus et magnis dis parturient montes, nascetur ridiculus mus. Quisque sed erat nec justo posuere suscipit. Donec ut efficitur arcu, in malesuada neque. Nunc dignissim nisl massa, id vulputate nunc pretium nec. Quisque eget urna in risus suscipit ultricies. Pellentesque odio odio, tincidunt in eleifend sed, posuere a diam. Nam gravida nisl convallis semper elementum. Morbi vitae felis faucibus, vulputate orci placerat, aliquet nisi. Aliquam erat volutpat. Maecenas sagittis pulvinar purus, sed porta quam laoreet at.\n","date":1461715200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1461715200,"objectID":"e8f8d235e8e7f2efd912bfe865363fc3","permalink":"https://nverma1.github.io/project/example/","publishdate":"2016-04-27T00:00:00Z","relpermalink":"/project/example/","section":"project","summary":"An example of using the in-built project page.","tags":["Deep Learning"],"title":"Example Project","type":"project"}]