softmax
FDE interview questions tagged softmax, across every topic.
2 questions · 0 unlocked for you
Concepts behind "softmax"
The curriculum that explains the ideas these questions test.
Foundational
Activation FunctionsWithout a non-linear activation, stacking layers is pointless: the whole network collapses into one linear map. Sigmoid and tanh saturate and kill gradients in deep nets, ReLU fixed that but invented dead neurons, and LeakyReLU, GELU and SiLU patch the dead-neuron problem. Softmax is for outputs, not hidden layers.📊 Evaluation & ML Foundations
Core
Numerical StabilityWhen you implement softmax, cross-entropy, or a running average by hand, the naive formula overflows or loses precision on real inputs. The fixes are a small, reusable toolkit: subtract the max before exponentiating, work in log space with log-sum-exp, and accumulate carefully. ML-adjacent coding screens lean on this, because the candidate who writes exp of a large logit and gets inf has shipped a silent bug.💻 Coding & Engineering CraftSign in