<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
</head>
<body dir="ltr">
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif;" dir="ltr">
<p style="margin-top:0;margin-bottom:0">Hello fellow data-scientists!</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">I've attached my very sparse notes regarding weeks 1 and 2. If you haven't already caught up on the course, I encourage you to do so!</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">Wojteks notebook: <a href="https://colab.research.google.com/drive/1g_Ev4zxFUq2twP0to9UPYW4iTHuZukTY" class="OWAAutoLink" id="LPlnk299757" previewremoved="true">
https://colab.research.google.com/drive/1g_Ev4zxFUq2twP0to9UPYW4iTHuZukTY</a><br>
</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">If you missed a bit of material and are looking to play catch-up on machine learning basics, you can check out the following articles:</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">(Very brief, but good) Towards Data Science:
<a href="https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6" class="OWAAutoLink" id="LPlnk50020" previewremoved="true">
https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6</a></p>
<div id="LPBorder_GT_15476848546570.29845366068334533" style="margin-bottom: 20px; overflow: auto; width: 100%; text-indent: 0px;">
<table id="LPContainer_15476848546500.6801689300803753" style="width: 90%; background-color: rgb(255, 255, 255); position: relative; overflow: auto; padding-top: 20px; padding-bottom: 20px; margin-top: 20px; border-top: 1px dotted rgb(200, 200, 200); border-bottom: 1px dotted rgb(200, 200, 200);" role="presentation" cellspacing="0">
<tbody>
<tr style="border-spacing: 0px;" valign="top">
<td id="ImageCell_15476848546510.583619653507727" style="width: 250px; position: relative; display: table-cell; padding-right: 20px;" colspan="1">
<div id="LPImageContainer_15476848546510.38040419315247465" style="background-color: rgb(255, 255, 255); height: 150px; position: relative; margin: auto; display: table; width: 250px;">
<a id="LPImageAnchor_15476848546520.29379537619858986" style="display: table-cell; text-align: center;" href="https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6" target="_blank"><img style="display: inline-block; max-width: 250px; max-height: 250px; height: 150px; width: 250px; border-width: 0px; vertical-align: bottom;" id="LPThumbnailImageID_15476848546520.13602916087282368" width="250" height="150" src="https://cdn-images-1.medium.com/max/1200/1*36MELEhgZsPFuzlZvObnxA.gif"></a></div>
</td>
<td id="TextCell_15476848546530.08298882431768317" style="vertical-align: top; position: relative; padding: 0px; display: table-cell;" colspan="2">
<div id="LPRemovePreviewContainer_15476848546540.5089831279977169"></div>
<div id="LPTitle_15476848546540.7038468118914817" style="top: 0px; color: rgb(0, 120, 215); font-weight: 400; font-size: 21px; font-family: "wf_segoe-ui_light", "Segoe UI Light", "Segoe WP Light", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; line-height: 21px;">
<a id="LPUrlAnchor_15476848546540.3828147533320526" style="text-decoration: none;" href="https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6" target="_blank">How to build your own Neural Network from scratch
in Python</a></div>
<div id="LPMetadata_15476848546550.6896130725198562" style="margin: 10px 0px 16px; color: rgb(102, 102, 102); font-weight: 400; font-family: "wf_segoe-ui_normal", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; font-size: 14px; line-height: 14px;">
towardsdatascience.com</div>
<div id="LPDescription_15476848546560.26584728158604454" style="display: block; color: rgb(102, 102, 102); font-weight: 400; font-family: "wf_segoe-ui_normal", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; font-size: 14px; line-height: 20px; max-height: 100px; overflow: hidden;">
Motivation: As part of my personal journey to gain a better understanding of Deep Learning, I’ve decided to build a Neural Network from scratch without a deep learning library like TensorFlow. I…</div>
</td>
</tr>
</tbody>
</table>
</div>
<p></p>
<p style="margin-top:0;margin-bottom:0">(Much longer, but in depth) Neural Networks and Deep learning:
<a href="http://neuralnetworksanddeeplearning.com/chap1.html" class="OWAAutoLink" id="LPlnk507336" previewremoved="true">
http://neuralnetworksanddeeplearning.com/chap1.html</a></p>
<div id="LPBorder_GT_15476848966140.426348421727588" style="margin-bottom: 20px; overflow: auto; width: 100%; text-indent: 0px;">
<table id="LPContainer_15476848966110.14404284291088465" style="width: 90%; background-color: rgb(255, 255, 255); position: relative; overflow: auto; padding-top: 20px; padding-bottom: 20px; margin-top: 20px; border-top: 1px dotted rgb(200, 200, 200); border-bottom: 1px dotted rgb(200, 200, 200);" role="presentation" cellspacing="0">
<tbody>
<tr style="border-spacing: 0px;" valign="top">
<td id="TextCell_15476848966110.21565668374569313" style="vertical-align: top; position: relative; padding: 0px; display: table-cell;" colspan="2">
<div id="LPRemovePreviewContainer_15476848966110.00692914537815692"></div>
<div id="LPTitle_15476848966120.41418474670874217" style="top: 0px; color: rgb(0, 120, 215); font-weight: 400; font-size: 21px; font-family: "wf_segoe-ui_light", "Segoe UI Light", "Segoe WP Light", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; line-height: 21px;">
<a id="LPUrlAnchor_15476848966120.55238435783975" style="text-decoration: none;" href="http://neuralnetworksanddeeplearning.com/chap1.html" target="_blank">Neural networks and deep learning</a></div>
<div id="LPMetadata_15476848966120.6174603244124838" style="margin: 10px 0px 16px; color: rgb(102, 102, 102); font-weight: 400; font-family: "wf_segoe-ui_normal", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; font-size: 14px; line-height: 14px;">
neuralnetworksanddeeplearning.com</div>
<div id="LPDescription_15476848966130.4069982519835683" style="display: block; color: rgb(102, 102, 102); font-weight: 400; font-family: "wf_segoe-ui_normal", "Segoe UI", "Segoe WP", Tahoma, Arial, sans-serif; font-size: 14px; line-height: 20px; max-height: 100px; overflow: hidden;">
If $\sigma$ had in fact been a step function, then the sigmoid neuron would be a perceptron, since the output would be $1$ or $0$ depending on whether $w\cdot x+b ...</div>
</td>
</tr>
</tbody>
</table>
</div>
If you have any questions/concerns/comments, or if you would like to volunteer to teach a lesson, let me know!
<p></p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">Cheers,</p>
<p style="margin-top:0;margin-bottom:0">David Livermore<br>
</p>
</div>
</body>
</html>