From perceptrons to transformers - visualize, experiment, and build AI with interactive code demos.
Learn how neurons process data through weighted inputs, activation functions, and backpropagation. Visualize feedforward and convolutional architectures.
Master gradient descent variants, learning rate schedules, and regularization strategies that prevent overfitting in complex models.
Explore RNNs, LSTMs, and transformers for processing sequential data in NLP and time series analysis.
Understand GANs, VAEs, and diffusion models for creating synthetic data, art, and content generation.
// Neural network demo
import torch
import torch.nn as nn
class SimpleNet(nn.Module):
def __init__(self):
super().__init__()
self.network = nn.Sequential(
nn.Linear(784, 256),
nn.ReLU(),
nn.Linear(256, 10)
)
def forward(self, x):
return self.network(x)
Complete textbook by Ian Goodfellow covering mathematical and conceptual foundations.
View PDF30+ hours of video lectures on neural networks, optimization, and real-world applications.
Watch VideosCurated list of foundational and modern deep learning research manuscripts.
Read Papers