Simplified renaming of various core functions and classes

README.md

@@ -56,12 +56,12 @@ import torch, torchhd
 d = 10000  # number of dimensions
 
 # create the hypervectors for each symbol
-keys = torchhd.random_hv(3, d)
+keys = torchhd.random(3, d)
 country, capital, currency = keys
 
-usa, mex = torchhd.random_hv(2, d)  # United States and Mexico
-wdc, mxc = torchhd.random_hv(2, d)  # Washington D.C. and Mexico City
-usd, mxn = torchhd.random_hv(2, d)  # US Dollar and Mexican Peso
+usa, mex = torchhd.random(2, d)  # United States and Mexico
+wdc, mxc = torchhd.random(2, d)  # Washington D.C. and Mexico City
+usd, mxn = torchhd.random(2, d)  # US Dollar and Mexican Peso
 
 # create country representations
 us_values = torch.stack([usa, wdc, usd])
@@ -77,7 +77,7 @@ mx_us = torchhd.bind(torchhd.inverse(us), mx)
 usd_of_mex = torchhd.bind(mx_us, usd)
 
 memory = torch.cat([keys, us_values, mx_values], dim=0)
-torchhd.cos_similarity(usd_of_mex, memory)
+torchhd.cosine_similarity(usd_of_mex, memory)
 # tensor([-0.0062,  0.0123, -0.0057, -0.0019, -0.0084, -0.0078,  0.0102,  0.0057,  0.3292])
 # The hypervector for the Mexican Peso is the most similar.
 ```
@@ -87,10 +87,10 @@ This example is from the paper [What We Mean When We Say "What's the Dollar of M
 ## Supported HDC/VSA models
 Currently, the library supports the following HDC/VSA models:
 
-- [Multiply-Add-Permute (MAP)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.MAP.html)
-- [Binary Spatter Codes (BSC)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.BSC.html)
-- [Holographic Reduced Representations (HRR)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.HRR.html)
-- [Fourier Holographic Reduced Representations (FHRR)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.FHRR.html)
+- [Multiply-Add-Permute (MAP)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.MAPTensor.html)
+- [Binary Spatter Codes (BSC)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.BSCTensor.html)
+- [Holographic Reduced Representations (HRR)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.HRRTensor.html)
+- [Fourier Holographic Reduced Representations (FHRR)](https://torchhd.readthedocs.io/en/stable/generated/torchhd.FHRRTensor.html)
 
 We welcome anyone to help with contributing more models to the library!
 

docs/getting_started.rst

@@ -33,13 +33,13 @@ The first step to encode these records is to define the basis-hypervectors for e
 
 .. code-block:: python
 
-	from torchhd import functional
+	import torchhd
 
 	d = 10000 # dimensions
-	fruits = functional.random_hv(3, d)
-	weights = functional.level_hv(10, d)
-	seasons = functional.circular_hv(4, d)
-	var = functional.random_hv(3, d)
+	fruits = torchhd.random(3, d)
+	weights = torchhd.level(10, d)
+	seasons = torchhd.circular(4, d)
+	var = torchhd.random(3, d)
 
 which creates hypervectors for the 3 fruit types, 10 weight levels, 4 seasons and the 3 variables. The figure below illustrates the distance between the pairs of hypervectors in each set:
 
@@ -55,7 +55,7 @@ Similar behavior can be achieved using the classes in the :ref:`embeddings` modu
 
 	weight = torch.tensor([149.0])
 	# explicit mapping of the fruit weight to an index
-	w_i = functional.value_to_index(weight, 0, 200, 10)
+	w_i = torchhd.functional.value_to_index(weight, 0, 200, 10)
 	weights[w_i]  # select representation of 149
 
 whereas the :ref:`embeddings<embeddings>` have this common behavior built-in:
@@ -75,10 +75,10 @@ Once the basis-hypervectors are defined, we can use the MAP operations from :ref
 
 .. code-block:: python
 
-	f = functional.bind(var[0], fruits[0])   # fruit = apple
-	w = functional.bind(var[1], weights[w_i]) # weight = 149
-	s = functional.bind(var[2], seasons[3])   # season = fall
-	r1 = functional.bundle(functional.bundle(f, w), s)
+	f = torchhd.bind(var[0], fruits[0])   # fruit = apple
+	w = torchhd.bind(var[1], weights[w_i]) # weight = 149
+	s = torchhd.bind(var[2], seasons[3])   # season = fall
+	r1 = torchhd.bundle(torchhd.bundle(f, w), s)
 
 which is equivalent to using the following shortened syntax:
 
@@ -95,7 +95,7 @@ Alternatively, we can use one of the commonly used encodings provided in the :re
 
 	# combine values in one tensor of shape (3, d)
 	values = torch.stack([fruits[0], weights[w_i], seasons[3]])
-	r1 = functional.hash_table(var, values)
+	r1 = torchhd.hash_table(var, values)
 
 The :ref:`structures` module contains the same encoding patterns in addition to binary trees and finite state automata, but provides them as data structures. This module provides class-based implementations of HDC data structures. Using the hash table class, record :math:`r_1` can be represented as follows:
 

docs/memory.rst

@@ -9,4 +9,4 @@ torchhd.memory
     :toctree: generated/
     :template: class.rst
 
-    SDM
+    SparseDistributed

docs/torchhd.rst

@@ -14,12 +14,12 @@ Basis-hypervector sets
     :toctree: generated/
     :template: function.rst
 
-    empty_hv
-    identity_hv
-    random_hv
-    level_hv
-    thermometer_hv
-    circular_hv
+    empty
+    identity
+    random
+    level
+    thermometer
+    circular
 
 
 Operations
@@ -50,7 +50,7 @@ Similarities
     :toctree: generated/
     :template: function.rst
 
-    cos_similarity
+    cosine_similarity
     dot_similarity
     hamming_similarity
 
@@ -79,11 +79,11 @@ VSA Models
     :toctree: generated/
     :template: class.rst
 
-    VSA_Model
-    BSC
-    MAP
-    HRR
-    FHRR
+    VSATensor
+    BSCTensor
+    MAPTensor
+    HRRTensor
+    FHRRTensor
 
 
 Utilities
@@ -93,7 +93,7 @@ Utilities
     :toctree: generated/
     :template: function.rst
 
-    as_vsa_model
+    ensure_vsa_tensor
     map_range
     value_to_index
     index_to_value

examples/hd_hashing.py

@@ -14,7 +14,7 @@ def __init__(self, levels: int, dimensions: int, device=None):
         self.dimensions = dimensions
         self.device = device
 
-        self.hvs = torchhd.circular_hv(levels, dimensions, device=device)
+        self.hvs = torchhd.circular(levels, dimensions, device=device)
         self.servers = []
         self.server_hvs = []
         self.weight_by_server = {}

torchhd/__init__.py

@@ -6,20 +6,20 @@
 import torchhd.datasets as datasets
 import torchhd.utils as utils
 
-from torchhd.base import VSA_Model
-from torchhd.bsc import BSC
-from torchhd.map import MAP
-from torchhd.hrr import HRR
-from torchhd.fhrr import FHRR
+from torchhd.tensors.base import VSATensor
+from torchhd.tensors.bsc import BSCTensor
+from torchhd.tensors.map import MAPTensor
+from torchhd.tensors.hrr import HRRTensor
+from torchhd.tensors.fhrr import FHRRTensor
 
 from torchhd.functional import (
-    as_vsa_model,
-    empty_hv,
-    identity_hv,
-    random_hv,
-    level_hv,
-    thermometer_hv,
-    circular_hv,
+    ensure_vsa_tensor,
+    empty,
+    identity,
+    random,
+    level,
+    thermometer,
+    circular,
     bind,
     bundle,
     permute,
@@ -31,8 +31,10 @@
     multirandsel,
     soft_quantize,
     hard_quantize,
-    cos_similarity,
+    cosine_similarity,
+    cos,
     dot_similarity,
+    dot,
     hamming_similarity,
     multiset,
     multibundle,
@@ -53,25 +55,25 @@
 
 __all__ = [
     "__version__",
-    "VSA_Model",
-    "BSC",
-    "MAP",
-    "HRR",
-    "FHRR",
+    "VSATensor",
+    "BSCTensor",
+    "MAPTensor",
+    "HRRTensor",
+    "FHRRTensor",
     "functional",
     "embeddings",
     "structures",
     "models",
     "memory",
     "datasets",
     "utils",
-    "as_vsa_model",
-    "empty_hv",
-    "identity_hv",
-    "random_hv",
-    "level_hv",
-    "thermometer_hv",
-    "circular_hv",
+    "ensure_vsa_tensor",
+    "empty",
+    "identity",
+    "random",
+    "level",
+    "thermometer",
+    "circular",
     "bind",
     "bundle",
     "permute",
@@ -83,8 +85,10 @@
     "multirandsel",
     "soft_quantize",
     "hard_quantize",
-    "cos_similarity",
+    "cosine_similarity",
+    "cos",
     "dot_similarity",
+    "dot",
     "hamming_similarity",
     "multiset",
     "multibundle",