Tag feed

#optimisation

18 posts1 followers

Trending tags this week

Hyperparameter Optimization: Grid vs Random vs Bayesian

2h ago · 20 min read · You've trained a Random Forest and it works — 85% accuracy out of the box. But you used the default hyperparameters. What if n_estimators=500 with max_features=0.3 and min_samples_leaf=10 pushes that

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Policy Gradients: REINFORCE from Scratch with NumPy

2d ago · 20 min read · In the DQN post, we trained a neural network to estimate Q-values and then picked the best action with argmax. That works when the action space is discrete — push left or push right. But what if you n

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Deep Q-Networks: Experience Replay and Target Networks

4d ago · 22 min read · In the Q-learning post, we trained an agent to navigate a 4×4 frozen lake using a simple lookup table — 16 states × 4 actions = 64 numbers. But what happens when the state space isn't a grid? CartPole

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Q-Learning from Scratch: Navigating the Frozen Lake

6d ago · 13 min read · Imagine you're standing on a frozen lake. Your goal is on the far side, but there are holes in the ice — fall in and it's game over. Worse, the ice is slippery: when you try to go right, you might sli

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Genetic Algorithms: From Line Fitting to the Travelling Salesman

6d ago · 14 min read · Imagine you're planning a road trip through 25 cities. The number of possible routes is 25!/2 — roughly 7.8 × 10²⁴, more than the number of stars in the observable universe. You can't try them all. An

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Backpropagation Demystified: Neural Nets from First Principles

Apr 2 · 15 min read · Every modern deep learning framework — PyTorch, TensorFlow, JAX — does one thing brilliantly: it computes gradients for you. Call loss.backward() and millions of parameters update simultaneously. But

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

From K-Means to GMM: Hard vs Soft Clustering

Mar 30 · 14 min read · You have a pile of unlabelled data and you want to find groups in it. K-Means is the algorithm everyone reaches for first — it's fast, simple, and usually works. But it makes a bold assumption: every

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Gaussian Mixture Models: The EM Algorithm in Practice

Mar 28 · 13 min read · You have a dataset that clearly contains distinct groups, but nobody has labelled them. K-Means would give you hard boundaries — each point belongs to exactly one cluster. But what if a data point sit

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

The EM Algorithm: An Intuitive Guide with the Coin Toss Example

Mar 27 · 11 min read · Imagine you're a casino inspector. You suspect a dealer has been switching between two biased coins, but you only have records of the outcomes - not which coin was used for each game. How do you figur

Join discussion

BSBerkan Sesensesenai.hashnode.dev

0

Maximum Likelihood Estimation from Scratch: From Coin Flips to Gaussians

Mar 26 · 15 min read · You've collected data and you have a model in mind — maybe a Gaussian, maybe a coin flip. But the model has parameters, and you need to find the values that best explain what you observed. How? Maximu

Join discussion

#optimisation

Search Hashnode

#optimisation

Trending tags this week

Hyperparameter Optimization: Grid vs Random vs Bayesian

Policy Gradients: REINFORCE from Scratch with NumPy

Deep Q-Networks: Experience Replay and Target Networks

Q-Learning from Scratch: Navigating the Frozen Lake

Genetic Algorithms: From Line Fitting to the Travelling Salesman

Backpropagation Demystified: Neural Nets from First Principles

From K-Means to GMM: Hard vs Soft Clustering

Gaussian Mixture Models: The EM Algorithm in Practice

The EM Algorithm: An Intuitive Guide with the Coin Toss Example

Maximum Likelihood Estimation from Scratch: From Coin Flips to Gaussians