How microsoft used the Neural Network for Speech Recognition.

So Hello guys,

Today we will be talking about the Neural Network how the companies using the Neural Network the topic is interesting but let me start from here,

What is a neural network?

AI may have come on in leaps and bounds in the last few years, but we’re still some way from truly intelligent machines – machines that can reason and make decisions like humans. Artificial neural networks (ANNs for short) may provide the answer to this.

Human brains are made up of connected networks of neurons. ANNs seek to simulate these networks and get computers to act like interconnected brain cells, so that they can learn and make decisions in a more humanlike manner.

Different parts of the human brain are responsible for processing different pieces of information, and these parts of the brain are arranged hierarchically, or in layers. In this way, as information comes into the brain, each level of neurons processes the information, provides insight, and passes the information to the next, more senior layer. For example, your brain may process the delicious smell of pizza wafting from a street café in multiple stages: ‘I smell pizza,’ (that’s your data input) … ‘I love pizza!’ (thought) … ‘I’m going to get me some of that pizza’ (decision making) … ‘Oh, but I promised to cut out junk food’ (memory) … ‘Surely one slice won’t hurt?’ (reasoning) ‘I’m doing it!’ (action).

It’s this layered approach to processing information and making decisions that ANNs are trying to simulate. In its simplest form, an ANN can have only three layers of neurons: the input layer (where the data enters the system), the hidden layer (where the information is processed) and the output layer (where the system decides what to do based on the data). But ANNs can get much more complex than that, and include multiple hidden layers. Whether it’s three layers or more, information flows from one layer to another, just like in the human brain.

Basics of Neural Networks

Neural networks, in the world of finance, assist in the development of such process as time-series forecasting, algorithmic trading, securities classification, credit risk modeling and constructing proprietary indicators and price derivatives.

A neural network works similarly to the human brain’s neural network. A “neuron” in a neural network is a mathematical function that collects and classifies information according to a specific architecture. The network bears a strong resemblance to statistical methods such as curve fitting and regression analysis.

A neural network contains layers of interconnected nodes. Each node is a perceptron and is similar to a multiple linear regression. The perceptron feeds the signal produced by a multiple linear regression into an activation function that may be nonlinear.

In a multi-layered perceptron (MLP), perceptrons are arranged in interconnected layers. The input layer collects input patterns. The output layer has classifications or output signals to which input patterns may map. For instance, the patterns may comprise a list of quantities for technical indicators about a security; potential outputs could be “buy,” “hold” or “sell.”

Hidden layers fine-tune the input weightings until the neural network’s margin of error is minimal. It is hypothesized that hidden layers extrapolate salient features in the input data that have predictive power regarding the outputs. This describes feature extraction, which accomplishes a utility similar to statistical techniques such as principal component analysis.

Types of Neural Networks in Artificial Intelligence

Four Different Techniques of ANNs

Classification Neural Network

In a Classification Neural Network, the network can be trained to classify any given patterns or datasets into a predefined class. It uses Feedforward Networks to do this.

Prediction Neural Network

In a Prediction Neural Network, the network can be trained to produce outputs that are expected from a given input. The network ‘learns’ to produce outputs that are similar to the representation examples given in the input

Clustering Neural Network

The Neural network can be used to identify a unique feature of the data and classify them into different categories without any prior knowledge of the data.

Following networks are used for clustering:

• Competitive networks
• Adaptive Resonance Theory Networks
• Kohonen Self-Organising Maps.

Association Neural Network

An Association Neural Network can be trained to remember a particular pattern, which enables any noise patterns presented to the network to be associated with with the closest one in the memory or discard it.

Microsoft Neural Network Algorithm

The Microsoft Neural Network algorithm is an implementation of the popular and adaptable neural network architecture for machine learning. The algorithm works by testing each possible state of the input attribute against each possible state of the predictable attribute, and calculating probabilities for each combination based on the training data. You can use these probabilities for both classification or regression tasks, to predict an outcome based on some input attributes. A neural network can also be used for association analysis.

When you create a mining model using the Microsoft Neural Network algorithm, you can include multiple outputs, and the algorithm will create multiple networks. The number of networks contained in a single mining model contains depends on the number of states (or attribute values) in the input columns, as well as the number of predictable columns that the mining model uses and the number of states in those columns.

Example(How microsoft use its Neural Network)

The Microsoft Neural Network algorithm is useful for analyzing complex input data, such as from a manufacturing or commercial process, or business problems for which a significant quantity of training data is available but for which rules cannot be easily derived by using other algorithms.

Suggested scenarios for using the Microsoft Neural Network algorithm include the following:

• Marketing and promotion analysis, such as measuring the success of a direct mail promotion or a radio advertising campaign
• Predicting stock movement, currency fluctuation, or other highly fluid financial information from historical data
• Analyzing manufacturing and industrial processes
• Text mining
• Any prediction model that analyzes complex relationships between many inputs and relatively fewer outputs

How the Algorithm Works

The Microsoft Neural Network algorithm creates a network that is composed of up to three layers of nodes (sometimes called neurons). These layers are the input layer, the hidden layer, and the output layer.

Input layer: Input nodes define all the input attribute values for the data mining model, and their probabilities.

Hidden layer: Hidden nodes receive inputs from input nodes and provide outputs to output nodes. The hidden layer is where the various probabilities of the inputs are assigned weights. A weight describes the relevance or importance of a particular input to the hidden node. The greater the weight that is assigned to an input, the more important the value of that input is. Weights can be negative, which means that the input can inhibit, rather than favor, a specific result.

Output layer: Output nodes represent predictable attribute values for the data mining model.

Data Required for Neural Network Models

A neural network model must contain a key column, one or more input columns, and one or more predictable columns.

Data mining models that use the Microsoft Neural Network algorithm are heavily influenced by the values that you specify for the parameters that are available to the algorithm. The parameters define how data is sampled, how data is distributed or expected to be distributed in each column, and when feature selection is invoked to limit the values that are used in the final model.

Creating Predictions

After the model has been processed, you can use the network and the weights stored within each node to make predictions. A neural network model supports regression, association, and classification analysis, Therefore, the meaning of each prediction might be different. You can also query the model itself, to review the correlations that were found and retrieve related statistics.

To know Detail about the microsoft Neural Network

Microsoft’s new neural text-to-speech service helps machines speak like people

Microsoft has reached a milestone in text-to-speech synthesis with a production system that uses deep neural networks to make the voices of computers nearly indistinguishable from recordings of people. With the human-like natural prosody and clear articulation of words, Neural TTS has significantly reduced listening fatigue when you interact with AI systems.

Neural text-to-speech can be used to make interactions with chatbots and virtual assistants more natural and engaging, convert digital texts such as e-books into audiobooks and enhance in-car navigation systems.

The milestone in text-to-speech joins a string of breakthroughs that our group has achieved over the past two years, including human parity in conversational speech recognition and human parity in machine translation.

By using the computational power of Azure, we can deliver real-time streaming, which is useful for situations such as interacting with a chatbot or virtual assistant. The capability is served in the Azure Kubernetes Service. This ensures high scalability and availability and gives customers the ability to use neural text-to-speech and traditional text-to-speech from a single endpoint.

You can try the Microsoft Speech recognition on below link

Learning Techniques in Neural Networks

Supervised Learning

In supervised learning, training data is ‘fed’ into the network, and the desired output is already predetermined. In supervised learning, weights are adjusted until production produces desired output.

Unsupervised Learning

The input data is used to train the network whose output is already known. The network classifies the input data and adjusts the weight by feature extraction in input data.

Reinforcement Learning

In reinforcement learning, the value of the output is unknown but the network provides the feedback on whether the output is right or wrong. This type of learning can also be known as semi-supervised learning.

Online Learning

The adjustment of the weight and threshold is made after presenting each training sample to the network.

Offline Learning

The adjustment of the weight vector and threshold is made only after all the training set is presented to the network. It is also called Batch Learning.

What are ANNs used for?

The main purpose of artificial neural networks was to solve problems and come up with reasoning in the same way that a human brain would. However, over time it was realised that ANN could be put to better use if it’s focus were shifted to performing specific tasks. This way, a ANN could be perfected for a specific task more efficiently, such as computer vision, speech recognition, machine translation, social network filtering, etc. Artificial neural networks in deep learning have even enabled machines to perform tasks that were previously thought to have been limited to humans, such as painting and creating music.

Hope you like it..

Any suggestions regarding this Please DM.

Thank you!!!??????