[DOC] Regression api

docs/source/api_reference/regression.rst

@@ -5,9 +5,9 @@ Time series regression
 
 The :mod:`sktime.regression` module contains algorithms and composition tools for time series regression.
 
-.. automodule:: sktime.regression
-    :no-members:
-    :no-inherited-members:
+All current sktime Regressors can be listed using the ``sktime.registry import
+all_estimators`` function.
+
 
 Composition
 -----------
@@ -20,6 +20,18 @@ Composition
 
     ComposableTimeSeriesForestRegressor
 
+Deep learning
+-------------
+
+.. currentmodule:: sktime.regression.deep_learning
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    CNNRegressor
+    TapNetRegressor
+
 Interval-based
 --------------
 
@@ -30,3 +42,33 @@ Interval-based
     :template: class.rst
 
     TimeSeriesForestRegressor
+
+Kernel-based
+------------
+
+.. currentmodule:: sktime.regression.kernel_based
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    RocketRegressor
+
+Base
+----
+
+.. currentmodule:: sktime.regression.base
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    BaseRegressor
+
+.. currentmodule:: sktime.regression.deep_learning.base
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    BaseDeepRegressor

sktime/regression/deep_learning/cnn.py

@@ -14,7 +14,7 @@
 
 
 class CNNRegressor(BaseDeepRegressor):
-    """Time Convolutional Neural Network (CNN), as described in [1].
+    """Time Series Convolutional Neural Network (CNN), as described in [1].
 
     Parameters
     ----------

sktime/regression/deep_learning/tapnet.py

@@ -16,7 +16,12 @@
 
 
 class TapNetRegressor(BaseDeepRegressor):
-    """Implementation of TapNetRegressor, as described in [1].
+    """Time series attentional prototype network (TapNet), as described in [1].
+
+     TapNet was initially proposed for multivariate time series
+     classification. The is an adaptation for time series regression. TapNet comprises
+     these components: random dimension permutation, multivariate time series
+     encoding, and attentional prototype learning.
 
     Parameters
     ----------