derbydefi

## talbot.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Talbot Effect Simulation</title>
    <style>
        body { display: flex; flex-direction: column; align-items: center; margin: 0; }
        canvas { border: 1px solid black; }
        .controls { margin: 10px; display: flex; flex-direction: column; align-items: center; }

## elm_activations.py
import time
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn.functional as F

#custom activations
def gelu_variant(x):
    two_over_pi = torch.tensor(2 / torch.pi, device=x.device)
    return 0.5 * x * (1 + torch.tanh(torch.sqrt(two_over_pi) * (x + 0.044715 * torch.pow(x, 3))))

## nls_ssf.py
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.animation import FuncAnimation, writers
from numpy.fft import fft, ifft

# Reduced setup for quicker testing
L = 30
N = 512  # Reduced number of spatial points for simplicity
dx = L / N
dt = 0.1  # Time step size can be adjusted if needed

## index.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Particle Simulation</title>
    <style>
        body {
            display: flex;
            justify-content: center;

## elm.py
import time
import torch
import torchvision
import torchvision.transforms as transforms

class ELM(torch.nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(ELM, self).__init__()
        self.hidden_size = hidden_size
        self.input_weights = torch.nn.Parameter(torch.randn(input_size, hidden_size) * 0.1, requires_grad=False)
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>Talbot Effect Simulation</title>
	<style>
	body { display: flex; flex-direction: column; align-items: center; margin: 0; }
	canvas { border: 1px solid black; }
	.controls { margin: 10px; display: flex; flex-direction: column; align-items: center; }
	import time
	import torch
	import torchvision
	import torchvision.transforms as transforms
	import torch.nn.functional as F

	#custom activations
	def gelu_variant(x):
	two_over_pi = torch.tensor(2 / torch.pi, device=x.device)
	return 0.5 * x * (1 + torch.tanh(torch.sqrt(two_over_pi) * (x + 0.044715 * torch.pow(x, 3))))
	import numpy as np
	import matplotlib.pyplot as plt
	from matplotlib.animation import FuncAnimation, writers
	from numpy.fft import fft, ifft

	# Reduced setup for quicker testing
	L = 30
	N = 512 # Reduced number of spatial points for simplicity
	dx = L / N
	dt = 0.1 # Time step size can be adjusted if needed