Perceptron (P) - Revision history

BPeat at 02:38, 6 March 2024

2024-03-06T02:38:49Z

BPeat at 14:13, 6 August 2023

2023-08-06T14:13:06Z

BPeat at 10:10, 14 July 2023

2023-07-14T10:10:35Z

BPeat at 10:07, 14 July 2023

2023-07-14T10:07:03Z

BPeat at 10:05, 14 July 2023

2023-07-14T10:05:23Z

BPeat at 02:09, 12 July 2023

2023-07-12T02:09:52Z

BPeat at 18:16, 2 July 2023

2023-07-02T18:16:27Z

BPeat at 18:15, 2 July 2023

2023-07-02T18:15:46Z

BPeat at 18:12, 9 May 2023

2023-05-09T18:12:14Z

BPeat at 02:58, 1 April 2023

2023-04-01T02:58:52Z

@@ Line 17: / Line 17: @@
 [http://www.google.com/search?q=perceptron+deep+machine+learning+ML+artificial+intelligence ...Google search]
-* [[AI Solver]] ... [[Algorithms]] ... [[Algorithm Administration|Administration]] ... [[Model Search]] ... [[Discriminative vs. Generative]] ... [[Optimizer]] ... [[Train, Validate, and Test]]
+* [[AI Solver]] ... [[Algorithms]] ... [[Algorithm Administration|Administration]] ... [[Model Search]] ... [[Discriminative vs. Generative]] ... [[Train, Validate, and Test]]
 ** [[...predict categories]]
 * [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]

@@ Line 35: / Line 35: @@
 The history of the Perceptron dates back to the late 1950s when it was introduced by Frank Rosenblatt, an American psychologist and computer scientist. Rosenblatt was inspired by the functioning of the human brain and aimed to develop a computational model that emulates the behavior of biological neurons.
-The Perceptron is based on the concept of a threshold logic unit (TLU), which mimics the behavior of a biological neuron. It takes a set of input values, applies weights to them, and produces an output based on a threshold activation function. The activation function determines whether the neuron fires or not based on the weighted sum of the inputs.
+The Perceptron is based on the concept of a threshold logic unit (TLU), which mimics the behavior of a biological neuron. It takes a set of input values, applies [[Activation Functions#Weights|weights]] to them, and produces an output based on a threshold activation function. The activation function determines whether the neuron fires or not based on the [[Activation Functions#Weights|weighted]] sum of the inputs.
-Rosenblatt's Perceptron was designed as a single-layer neural network with adjustable weights, capable of learning from training examples through a process called supervised learning. The weights are updated iteratively to minimize the error between the predicted output and the desired output. This learning process is known as the perceptron learning rule or the delta rule.
+Rosenblatt's Perceptron was designed as a single-layer neural network with adjustable [[Activation Functions#Weights|weights]], capable of learning from training examples through a process called supervised learning. The [[Activation Functions#Weights|weights]] are updated iteratively to minimize the error between the predicted output and the desired output. This learning process is known as the perceptron learning rule or the delta rule.
 The Perceptron gained attention in the AI community because it demonstrated the capability of learning and making decisions based on training data. Rosenblatt and his colleagues conducted experiments with Perceptrons to show their ability to classify simple patterns, such as distinguishing between different shapes. These early successes raised hopes that the Perceptron could solve more complex problems and even replicate human-like intelligence.
@@ Line 52: / Line 52: @@
 = Threshold Logic Unit (TLU) =
-A Threshold Logic Unit (TLU) is a simple processing unit for real-valued numbers with multiple inputs and a single output. The unit has a threshold and each input is associated with a weight. The TLU computes a weighted sum of its inputs, compares this to the threshold, and outputs 1 if the threshold is exceeded.
+A Threshold Logic Unit (TLU) is a simple processing unit for real-valued numbers with multiple inputs and a single output. The unit has a threshold and each input is associated with a [[Activation Functions#Weights|weight]]. The TLU computes a [[Activation Functions#Weights|weighted]] sum of its inputs, compares this to the threshold, and outputs 1 if the threshold is exceeded.
 The TLU is a basic form of machine learning model and is the most basic form of AI-neuron or computational unit. It is also known as a perceptron.
 The history of Deep Learning is often traced back to 1943 when Walter Pitts and Warren McCulloch created a computer model that supported the neural networks of the human brain. They used a mixture of algorithms and arithmetic they called “threshold logic” to mimic the thought process.
@@ Line 70: / Line 70: @@
 * [http://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/two-class-averaged-perceptron Two-Class Averaged Perceptron | Microsoft]
-The averaged perceptron method is an early and very simple version of a neural network. In this approach, inputs are classified into several possible outputs based on a linear function, and then combined with a set of weights that are derived from the feature vector—hence the name "perceptron."
+The averaged perceptron method is an early and very simple version of a neural network. In this approach, inputs are classified into several possible outputs based on a linear function, and then combined with a set of [[Activation Functions#Weights|weights]] that are derived from the feature vector—hence the name "perceptron."
 <youtube>iVbBIAgTJ2M</youtube>

@@ Line 20: / Line 20: @@
 ** [[...predict categories]]
 * [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]
-** [[Neural Network#Neural Network History|Neural Network History]]
+* [[History of Artificial Intelligence (AI)]] ... [[Neural Network#Neural Network History|Neural Network History]] ... [[Creatives]]
 * [http://www.asimovinstitute.org/author/fjodorvanveen/ Neural Network Zoo | Fjodor Van Veen]
 * [http://en.wikipedia.org/wiki/Perceptron Wikipedia]

@@ Line 21: / Line 21: @@
 * [[What is Artificial Intelligence (AI)? | Artificial Intelligence (AI)]] ... [[Machine Learning (ML)]] ... [[Deep Learning]] ... [[Neural Network]] ... [[Reinforcement Learning (RL)|Reinforcement]] ... [[Learning Techniques]]
 ** [[Neural Network#Neural Network History|Neural Network History]]
 * [http://www.asimovinstitute.org/author/fjodorvanveen/ Neural Network Zoo | Fjodor Van Veen]
 * [http://en.wikipedia.org/wiki/Perceptron Wikipedia]

@@ Line 30: / Line 30: @@
 http://ataspinar.com/wp-content/uploads/2016/11/perceptron_schematic_overview.png
 https://appliedgo.net/media/perceptron/pointsandline.png
 <youtube>ntKn5TPHHAk</youtube>

@@ Line 2: / Line 2: @@
 |title=PRIMO.ai
 |titlemode=append
-|keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, Microsoft, Azure, Amazon, AWS
+|keywords=ChatGPT, artificial, intelligence, machine, learning, GPT-4, GPT-5, NLP, NLG, NLC, NLU, models, data, singularity, moonshot, Sentience, AGI, Emergence, Moonshot, Explainable, TensorFlow, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Hugging Face, OpenAI, Tensorflow, OpenAI, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Meta, LLM, metaverse, assistants, agents, digital twin, IoT, Transhumanism, Immersive Reality, Generative AI, Conversational AI, Perplexity, Bing, You, Bard, Ernie, prompt Engineering LangChain, Video/Image, Vision, End-to-End Speech, Synthesize Speech, Speech Recognition, Stanford, MIT |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools
 }}
 [http://www.youtube.com/results?search_query=perceptron YouTube search...]

@@ Line 11: / Line 11: @@
 ** [[...predict categories]]
 * [[Capabilities]]
-* [[Deep Neural Network (DNN)]]
+* [[Neural Network]]
-** [[Deep Neural Network (DNN)#Neural Network History|Neural Network History]]
+** [[Neural Network#Neural Network History|Neural Network History]]
 * [http://www.asimovinstitute.org/author/fjodorvanveen/ Neural Network Zoo | Fjodor Van Veen]
 * [http://en.wikipedia.org/wiki/Perceptron Wikipedia]