Welcome to my new blog! I’ll be writing about machine learning, distributed systems, and other topics that interest me.

What to Expect

This blog will cover:

• Deep Learning: Neural network architectures, training techniques, and practical insights
• Distributed Systems: Scaling ML workloads across multiple machines
• Reinforcement Learning: Algorithms, environments, and applications
• Engineering: Software engineering best practices for ML systems

LaTeX Support

This blog supports LaTeX for mathematical notation. Here are some examples:

Inline Math

The softmax function is defined as $\sigma(z_i) = \frac{e^{z_i}}{\sum_{j=1}^{K} e^{z_j}}$.

Display Math

The cross-entropy loss for multi-class classification:

\[\mathcal{L} = -\sum_{i=1}^{N} \sum_{c=1}^{C} y_{i,c} \log(p_{i,c})\]

More Examples

The policy gradient theorem in reinforcement learning:

\[\nabla_\theta J(\theta) = \mathbb{E}_{\pi_\theta} \left[ \nabla_\theta \log \pi_\theta(a|s) \cdot Q^{\pi_\theta}(s, a) \right]\]

Code Snippets

Here’s an example of defining a simple neural network in PyTorch:

import torch.nn as nn

class SimpleNet(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super().__init__()
        self.layers = nn.Sequential(
            nn.Linear(input_dim, hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, output_dim)
        )

    def forward(self, x):
        return self.layers(x)

Stay Tuned

More posts coming soon! Feel free to reach out on X or GitHub if you have questions or suggestions.