Skip to main content

 Refresher:

Adam (Adaptive Moment Estimation) Combines momentum (tracking exponentially decaying average of past gradients) with RMSprop (tracking exponentially decaying average of squared gradients) to adapt learning rates for each parameter individually. Uses bias correction to account for initialization at zero, making it particularly effective early in training. Widely used default optimizer that typically works well across many problems with minimal hyperparameter tuning.

AdaGrad (Adaptive Gradient) Accumulates the sum of squared gradients for each parameter throughout training and divides the learning rate by the square root of this accumulated value. Works well for sparse data and parameters that receive infrequent updates, giving them larger effective learning rates. Major drawback is that the accumulated squared gradients grow monotonically, causing learning rates to eventually become vanishingly small and training to stop.

RMSprop (Root Mean Square Propagation) Addresses AdaGrad's diminishing learning rate problem by using an exponentially decaying average of squared gradients instead of accumulating all historical values. Maintains separate adaptive learning rates for each parameter while allowing continued learning throughout training. Particularly effective for non-stationary objectives and problems with noisy gradients like mini-batch training.

AdaDelta Extension of RMSprop that eliminates the need for a default learning rate by replacing it with an exponentially decaying average of squared parameter updates from previous steps. Ensures that parameter updates have consistent units/magnitudes by forming a ratio between the RMS of parameter updates and RMS of gradients. More robust to hyperparameter choices but adds computational overhead by tracking additional running averages.


Comments

Post a Comment

Popular posts from this blog

Simple Linear Regression - and Related Regression Loss Functions

Today's Topics: a. Regression Algorithms  b. Outliers - Explained in Simple Terms c. Common Regression Metrics Explained d. Overfitting and Underfitting e. How are Linear and Non Linear Regression Algorithms used in Neural Networks [Future study topics] Regression Algorithms Regression algorithms are a category of machine learning methods used to predict a continuous numerical value. Linear regression is a simple, powerful, and interpretable algorithm for this type of problem. Quick Example: These are the scores of students vs. the hours they spent studying. Looking at this dataset of student scores and their corresponding study hours, can we determine what score someone might achieve after studying for a random number of hours? Example: From the graph, we can estimate that 4 hours of daily study would result in a score near 80. It is a simple example, but for more complex tasks the underlying concept will be similar. If you understand this graph, you will understand this blog. Sim...
Post a Comment
Read more

What problems can AI Neural Networks solve

How does AI Neural Networks solve Problems? What problems can AI Neural Networks solve? Based on effectiveness and common usage, here's the ranking from best to least suitable for neural networks (Classification Problems, Regression Problems and Optimization Problems.) But first some Math, background and related topics as how the Neural Network Learn by training (Supervised Learning and Unsupervised Learning.)  Background Note - Mathematical Precision vs. Practical AI Solutions. Math can solve all these problems with very accurate results. While Math can theoretically solve classification, regression, and optimization problems with perfect accuracy, such calculations often require impractical amounts of time—hours, days, or even years for complex real-world scenarios. In practice, we rarely need absolute precision; instead, we need actionable results quickly enough to make timely decisions. Neural networks excel at this trade-off, providing "good enough" solutions in seco...
Post a Comment
Read more

Activation Functions in Neural Networks

  A Guide to Activation Functions in Neural Networks 🧠 Question: Without activation function can a neural network with many layers be non-linear? Answer: Provided at the end of this document. Activation functions are a crucial component of neural networks. Their primary purpose is to introduce non-linearity , which allows the network to learn the complex, winding patterns found in real-world data. Without them, a neural network, no matter how deep, would just be a simple linear model. In the diagram below the f is the activation function that receives input and send output to next layers. Commonly used activation functions. 1. Sigmoid Function 2. Tanh (Hyperbolic Tangent) 3. ReLU (Rectified Linear Unit - Like an Electronic Diode) 4. Leaky ReLU & PReLU 5. ELU (Exponential Linear Unit) 6. Softmax 7. GELU, Swish, and SiLU 1. Sigmoid Function                       The classic "S-curve," Sigmoid squashes any input value t...
Post a Comment
Read more