Ancestral reconstruction extrapolates characteristics back in time
Image: XiaYZ2023, CC BY-SA 4.0, via Wikimedia Commons
the reverse process learns: p_θ(x_{t-1}|x_t)
Ancestral reconstruction extrapolates characteristics back in time
Ancestral reconstruction is a method used in phylogenetics to trace the evolutionary history of species by studying the characteristics of modern organisms and working backward to infer the traits of common ancestors. This process helps scientists understand how species have evolved over millions of years.
Example
By analyzing the genetic sequences of modern organisms, scientists can reconstruct the genetic sequence of their common ancestors, providing insights into the evolutionary history of those species.
Remember this
Understanding ancestral traits helps researchers gain insights into the evolutionary processes that have shaped life on Earth.
Text adapted from Wikipedia, licensed under CC BY-SA 4.0.
Related concepts
Stable Diffusion
Stable Diffusion generates images from text descriptions
KV-cache reduces redundant computation in autoregressive generation
KV-cache stores previously computed outputs to avoid redundant calculations in autoregressive models
cross-entropy equals negative log-likelihood for classification
Why does knowing the wrong probability help us measure information loss?
log-loss / cross-entropy loss penalizes: confident wrong predictions more heavily
Cross-entropy loss penalizes confident wrong predictions more heavily
dropout works as regularization: it approximates an ensemble of subnetworks
Why does turning off neurons randomly help a brainy computer learn better?
gradient checkpointing trades: recomputes activations to save memory
Gradient checkpointing trades off computation time for memory savings by recomputing activations
Swipe through 100 ML concepts daily
Open Pocket Polymath