Loading video...

Video Failed to Load

Go Home

This one is easy: Eagles guard Jamon Brown 2020 Week 6 vs. Ravens: 2 sacks allowed 3 hurries allowed 4 QB hits allowed - Fixed gloves mid-play and let Wentz get pressured - Sacked Wentz by himself - Took a picture with Lamar after the Eagles lost He was...

3,451,874 views • 2 years ago •via X (Twitter)

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The King's Guard is famous for standing perfectly still, no matter what happens around him. On this day, one guard did something no one expected. Earlier that afternoon, a six-year-old boy named Oliver had been walking through the crowded plaza with his parents. He was excited to see the guards in their red uniforms and tall black hats, just like the pictures in his books. In the noise and movement of the crowd, his parents' hands slipped away. One second he felt safe, and the next he was surrounded by strangers. Fear took over. Tears blurred his vision as he pushed through coats and legs, calling for his parents while nothing around him looked familiar anymore. Looking for someone who felt safe, Oliver spotted the guard standing motionless in his sentry box. He ran straight toward him and grabbed the red coat with both hands. Please help me, he cried. The guard was trained to ignore distractions. He was trained not to react. Still, when he looked down and saw the terror on the child's face, instinct outweighed protocol. A glance at the clock inside the box showed one thing clearly. His shift ended in two minutes. In a calm, steady voice, he spoke without moving. Stay right here and don't move. I'll help you in one minute. Oliver stood beside him, gripping the coat, counting every second. At exactly the end of the shift, the next guard marched in and officially took over the post. Only then did the first guard step away. He knelt down immediately and opened his arms. Alright, buddy, he said gently. What's wrong? The boy's brave face collapsed. I can't find my mom, he sobbed. Oliver pressed into the guard's chest, shaking. The guard held him firmly and spoke in a low, reassuring voice. You're safe now. I've got you, and we're going to find her together. He stayed there with the child, unmoving and patient, until police located the frantic parents and reunited them. Everyone who witnessed the moment understood something important that day. Rules matter, but compassion matters more when a child is afraid.

Gabriele Corno

492,546 views • 5 days ago

MLP in PyTorch by hand ✍️ ~ 7 steps walkthrough below Goal: fill in every blank in the PyTorch code to build a multi-layer perceptron. 1. Given Let us start with a code template on the left and the network it is supposed to build on the right. Every blank in the code can be worked out from the picture. 2. Linear layer We count: 3 features in, 4 features out. So the weight matrix is 4 by 3. There is an extra column for the biases, which means bias = T. 3. ReLU Let us apply the activation. ReLU crosses out the negatives, so -1 becomes 0. 4. Linear layer The input size is 4, because that is what the previous layer put out. The output size is 2. A 2 by 4 weight matrix, and this time no extra column, so bias = F. 5. ReLU We cross out the negatives again. 6. Linear layer Two features in, five out. A 5 by 2 weight matrix, with a bias column, so bias = T. 7. Sigmoid Let us finish. Sigmoid squashes the raw scores (3, 0, -2, 5, -5) into probabilities between 0 and 1. You have just implemented a three-layer deep neural network by hand. ✍️ == Story == Three years ago I gave this exercise to my students, to connect the code to the math. They found it odd. Every other AI course they were taking lived inside a Jupyter notebook, and here I was handing out paper. Three years later, my colleagues are the ones rushing to move their materials to paper. The exercise has not changed. Paper still asks the one thing a notebook lets you skip: do you actually understand what the code is doing? If you can tell me why the weight matrix is 4 by 3, and why bias is F on the second layer, you understand nn.Linear better than someone who has been copy-pasting it for a year. 💾 Save this post! #AIbyHand #PyTorch #DeepLearning

Tom Yeh

13,318 views • 1 month ago

Batch Normalization by hand ✍️ ~ 7 steps walkthrough below Batch normalization is common practice for improving training and achieving faster convergence. It sounds simple. But it is often misunderstood. 🤔 Does batch normalization involve trainable parameters, tunable hyper-parameters, or both? 🤔 Is batch normalization applied to inputs, features, weights, biases, or outputs? 🤔 How is batch normalization different from layer normalization? So I drew and calculated one entirely by hand. Goal: normalize a mini-batch of 4 examples to mean 0 and variance 1, then let the network scale it back. = 1. Given = A mini-batch of 4 training examples, each with 3 features. = 2. Linear layer = Let us multiply by the weights and add the biases. Batch norm sits after this, which answers the second question: what gets normalized is features, not inputs, weights or biases. = 3. ReLU = We apply the activation, and -2 becomes 0. Negative values are suppressed before any statistic is taken. = 4. Batch statistics = Let us compute the sum, mean, variance and standard deviation, one row at a time. A row is a feature and the four columns are the four examples, so every number here measures one feature against the rest of the batch. That is the "batch" in batch normalization, and it is exactly what layer normalization does not do. The statistics are rounded to whole numbers, which is what keeps the rest of the page doable in pen. = 5. Shift to mean 0 = We subtract the mean, in green. The four values in each feature now average to zero. = 6. Scale to variance 1 = Let us divide by the standard deviation, in orange. Each feature now has variance one, whatever scale it arrived at. = 7. Scale and shift = We multiply by a linear transformation and pass the result on. The diagonal and the last column are trainable, so having just forced every feature to mean 0 and variance 1, we hand the network the means to undo it. The outputs: Mean of each feature = [2, 1, 2] Std dev of each feature = [1, 1, 2] To the next layer = [2, -2, 2, 0], [-3, 3, 6, -3], [2, 0, 1, 2] The answers: 🤔 Both. The scale and shift are trainable, the statistics are not. Epsilon and the momentum on the running statistics are the hyper-parameters, and one mini-batch by hand needs neither. 🤔 Features, after the linear layer, not inputs, weights or biases. 🤔 Batch norm measures across the batch, one feature at a time. Layer norm measures across the features, one example at a time. 💾 Save this post!

Tom Yeh

20,638 views • 1 month ago