Skip to main content
    Skip to main contentSkip to navigationSkip to footer
    Artificial Intelligence
    (Tanh (Hyperbolischer Tangens))

    Tanh (Hyperbolic Tangent)

    Also known as:
    Tanh Function
    Hyperbolic Tangent Activation
    Updated: 2/10/2026

    An activation function that maps values to the range [-1, 1] – zero-centered and smoother than sigmoid.

    Quick Summary

    Tanh maps values to [-1, 1] – zero-centered like ReLU, but smoother. Standard in LSTM/GRU gates, replaced by ReLU in feed-forward networks.

    Explanation

    Tanh is a scaled sigmoid: tanh(x) = 2σ(2x) - 1. The zero-centered property improves gradient flow compared to sigmoid.

    Marketing Relevance

    Tanh was long the standard in RNNs and LSTMs. Replaced by ReLU/GELU in modern architectures, but still relevant in certain contexts (e.g., gate functions).

    Common Pitfalls

    Vanishing gradient problem at extreme values. More computationally expensive than ReLU. Saturation at |x| > 3.

    Origin & History

    Tanh became popular as an improvement over sigmoid in the 1990s (LeCun, 1998). The zero-centered property improved convergence. With the rise of ReLU (2010), importance decreased, but tanh remains standard in LSTM/GRU gates.

    Comparisons & Differences

    Tanh (Hyperbolic Tangent) vs. Sigmoid

    Sigmoid maps to [0, 1] (not zero-centered); Tanh to [-1, 1] (zero-centered) – Tanh often converges faster.

    Tanh (Hyperbolic Tangent) vs. ReLU

    ReLU is faster to compute and avoids vanishing gradients for positive values. Tanh is smoother but saturates at extreme inputs.

    Related Services

    Related Terms

    👋Questions? Chat with us!