Загрузка видео...
Не удалось загрузить видео
Air Raid Offense High School Spring Install (First Year) #1 Pass Offense in Tennessee 2023 2 Form: Open, Blu/Blu Flip 2 Run: 30 (Dive), 34/35 (Iso) 4 Quick: Hitch, Friday, Stick, Corner 5 Drop: 6, Shallow, Mesh, Y Sail, Y Cross Master basics in spring, expand in summer!
26,165 просмотров • 1 год назад •via X (Twitter)
Комментарии: 11
Or just go with that spring install for the season, add a couple of screens and score 60 per game 😎 Good stuff
Only issue in high school is the wide hashes. I feel like 3x1 is almost vital running this system at this level.
BYU Cougars Shirt of the Month Get officially-licensed BYU Cougars T-shirts, long-sleeves & hoodies monthly
Do you have preferences calling plays only in specific formations?
Absolutely. As a whole in the passing game, 90% is: 2x2 - 6, Shallow, Quicks 3x1 - 6, Shallow, Mesh 2x1 - Mesh, Y Sail, Y Cross 3x2 - 6, Shallow, Outlaw
Love it!!
@stanbedwell my man what’s Friday? I forgot
Nice
That's awesome coach!!
Did you have the #1 pass offense with only these plays and formations that season or did you eventually add in trips and open flip, Rita and Lisa, etc?
We added those in the summer.
![Dropout by hand ✍️ ~ 10 steps walkthrough below Dropout is the simplest trick in deep learning that actually works: during training you randomly switch neurons off, so the network cannot lean on any one of them. It is two lines of code and almost nobody has worked through what those lines do to the numbers. So I drew and calculated one entirely by hand. Goal: train one pass through a small network with two dropout layers, then run inference with dropout switched off. The network: Linear(2,4), ReLU, Dropout(0.5), Linear(4,3), ReLU, Dropout(0.33), Linear(3,2). = 1. Given = A training set of two examples, X1 and X2, and the weight matrices for all three linear layers. = 2. Draw the first random numbers = Let us draw 4 random numbers, one per neuron in the first hidden layer. Above 0.5 we keep (◯), below we drop (╳). Here that gives [◯, ╳, ◯, ╳]. = 3. Build the first dropout matrix = We turn that pattern into a diagonal matrix. The scaling factor is 1/(1-p) = 2, so a kept neuron gets 2 and a dropped one gets 0. Multiplying by it does both jobs at once: it deletes the 2nd and 4th neurons and doubles the two that survive. = 4. Draw the second random numbers = Let us do it again for the 3 neurons in the next layer, this time against p = 0.33. The result is [◯, ◯, ╳]. = 5. Build the second dropout matrix = We set the diagonal to 1.5 where kept and 0 where dropped. Only the 3rd neuron goes. = 6. Feed forward = Let us run the whole thing top to bottom: one matrix multiplication per layer, ReLU setting the negatives to zero, and the two dropout matrices doing their work in between. The outputs Y come out at the bottom. = 7. MSE loss gradients = We compare Y against the targets Y', subtract, and multiply each element by 2. That is the whole gradient of the mean squared error. = 8. Update the weights = Let us push those gradients back through the network and update the weights (marked in light red). = 9. Deactivate dropout = Training is over, so we set both dropout matrices to the identity. Every neuron is back, and nothing is scaled. = 10. Feed forward again = One more pass, this time on unseen data, to make the prediction. You have just trained and run a network with dropout by hand. ✍️ The outputs: Training outputs Y = [-6, 9; 13, 4] Loss gradients = [-4, 4; 6, -2] Inference outputs = [13, 13; 4, 3] 💾 Save this post! #AIbyHand #Dropout #DeepLearning #NeuralNetworks](https://image.24vids.com/tw-2078846104460783996/ext_tw_video_thumb/2078846092997763074/pu/img/pljAsdaJjvGEEjPE.jpg)
