Navigation menu

** Reference source for IA**.

Sep 08, · Machine Learning Glossary. This glossary defines general machine learning terms as well as terms specific to TensorFlow. A. A/B testing. A statistical way of comparing two (or more) techniques, typically an incumbent against a new rival. Skin Rejuvenation Definition - Anti Aging Neck And Decollete Skin Rejuvenation Definition Organic Skin Care Specialists Columbus Ohio Essential Oil Anti Aging Cream.

As to the effect, in the United Kingdom, of a forged signature on a bill of exchange, see section 24 of the Bills of Exchange Act Before the invention of photography , people commonly hired painters and engravers to "re-create" an event or a scene. Artists had to imagine what to illustrate based on the information available to them about the subject. Some artists added elements to make the scene more exotic, while others removed elements out of modesty.

In the 18th century, for example, Europeans were curious about what North America looked like and were ready to pay to see illustrations depicting this faraway place.

Some of these artists produced prints depicting North America, despite many having never left Europe. From Wikipedia, the free encyclopedia. For the Soviet aircraft, see Yakovlev Yak For novels and films, see The Forger disambiguation. For the process of shaping metal by localized compressive forces, see Forging.

For other uses, see Forgery disambiguation. This article needs additional citations for verification. Please help improve this article by adding citations to reliable sources. Unsourced material may be challenged and removed. November Learn how and when to remove this template message. This section needs expansion. You can help by adding to it.

Boggs American artist, best known for his hand-drawn depictions of banknotes. Digitised copy of section 1.

Collins Dictionary of Law. Pages and Digitised copy of section Retrieved 20 July Immigrant Legal Resource Center1. Retrieved 1 August Richard; Bigelow, Tricia A. Office of Legislative Research. Retrieved 9 August Art of the Everyday: Dutch Painting and the Realist Novel.

Books-Authors 1 1 Misc. Hence Priority order for study: Not updated after only reprinted , but for IBPS level theory, its coverage is sufficient and you can always google for any latest happenings. Few MCQs after each chapter. Not updated after , just reprinted.

Handbook of Banking information by N. Most updated information about banking topics, among the given books. But also burdens you with many technical-legal aspects that are not much relevent from IBPS exam point of view.

Who is the current governor, whom did he replace? Name of their main bosses, Who controls what? How do they apply to Domestic bank vs foreign bank? Currency chest, Mint and press. Who signs coins and currency? Measures of money supply Foreign exchange management, components of forex reserves, approx. Basics What is bank? What are its functions? What is a Scheduled commercial bank? Public sector versus private sector banks. Where does RTI apply? Bank nationalization, mergers and consolidations.

Basic GK related to banks: Banking services Assets, liabilities and working capital of a bank. How do they apply to Domestic bank vs Foreign bank?

Which bank has highest NPA? RBI related Which of the following is a correct statement? State Bank of India is the sole authority to issue and manage currency in India.

A nationalised bank is the sole authority to issue and manage currency in India. A cooperative bank is the sole authority to issue and manage currency in India.

RBI is the sole authority to issue and manage currency in India. None of these By increasing repo rate, the economy may observe the following effects: Rate of interest on loans and advances will be costlier Industrial output would be affected to an extent Banks will increase rate of interest on deposits Industry houses may borrow money from foreign countries All of these Which of the following is NOT a function of the Reserve Bank of India? Regulated by State Governments.

Regulated by Central Government. Regulated by Finance minister. Banking services Which of the following statements is true? Banks cannot accept demand and time deposits from public. Banks can accept only demand deposits from public Banks can accept only time deposits from public Banks can accept both demand and time deposits from public.

Banks can accept demand and time deposits only from government. Under which Act criminal action can be initiated? Rajendra had filed a complaint with Banking Ombudsman but is not satisfied with the decision.

What is the next option him for getting his matter resolved? Who is its chairman and what is the purpose? Economy Theory Although in previous IBPS exams, within economy they gave more emphasis on current affairs over theory portion. Google as and when necessary.

Three types of Economies: Commercial bills, Treasury bills, certificate of deposit, commercial paper Derivatives, options-futures, currency swaps, underwriting, factoring debt vs equity: Ration at affordable cost to persons not yet given the same.

House at affordable cost to persons not yet given the same. Food at affordable cost to persons not yet given the same. Education at affordable cost to persons not yet given the same. When the rate of inflation increases purchasing power of money increases purchasing power of money decreases value of money increases purchasing power of money remains unaffected amount of money in circulation decreases When there is a difference between all receipts and expenditure of the Govt.

Major highlights of Budget click me Income tax slabs peak rates of excise, service tax and custom duty Negative list of Service tax. Weakening of the dollar might have pushed up Euro and other major currencies up and some European countries which were already in trouble would have faced a new crisis.

Debt limit was directly related to liquidity position of banks in USA. What was the reason for the same? India had a bumper crop of wheat during last two years. Hence it has excess stock of wheat. As per the Food Security Act, India is bound to provide 10 million tones of wheat to World food grain stock every year.

India defaulted last year. This year it does not want to be one. As advised by the Supreme Court of India, the money received from export should be used to pay subsidy to the farmers. Govt schemes Which of the following schemes of the Govt. The dot product of two embeddings is a measure of their similarity. Choosing the function that minimizes loss on the training set. Contrast with structural risk minimization. A merger of the predictions of multiple models.

You can create an ensemble via one or more of the following:. Deep and wide models are a kind of ensemble. A full training pass over the entire data set such that each example has been seen once. An instance of the tf. Estimator class, which encapsulates logic that builds a TensorFlow graph and runs a TensorFlow session. You may create your own custom Estimators as described here or instantiate premade Estimators created by others.

One row of a data set. An example contains one or more features and possibly a label. See also labeled example and unlabeled example. An example in which the model mistakenly predicted the negative class. For example, the model inferred that a particular email message was not spam the negative class , but that email message actually was spam. An example in which the model mistakenly predicted the positive class. For example, the model inferred that a particular email message was spam the positive class , but that email message was actually not spam.

The x-axis in an ROC curve. The false positive rate is defined as follows:. A function that specifies how a model should interpret a particular feature.

A list that collects the output returned by calls to such functions is a required parameter to all Estimators constructors. A synthetic feature formed by crossing taking a Cartesian product of individual binary features obtained from categorical data or from continuous features via bucketing.

Feature crosses help represent nonlinear relationships. The process of determining which features might be useful in training a model, and then converting raw data from log files and other sources into said features.

In TensorFlow, feature engineering often means converting raw log file entries to tf. The group of features your machine learning model trains on. For example, postal code, property size, and property condition might comprise a simple feature set for a model that predicts housing prices. Describes the information required to extract features data from the tf. Example protocol buffer is just a container for data, you must specify the following:. A machine learning approach, often used for object classification, designed to learn effective classifiers from only a small number of training examples.

Contrast with candidate sampling. A hidden layer in which each node is connected to every node in the subsequent hidden layer. A fully connected layer is also known as a dense layer. Abbreviation for generative adversarial network.

Refers to your model's ability to make correct predictions on new, previously unseen data as opposed to the data used to train the model. A generalization of least squares regression models, which are based on Gaussian noise , to other types of models based on other types of noise, such as Poisson noise or categorical noise. Examples of generalized linear models include:. The parameters of a generalized linear model can be found through convex optimization.

The power of a generalized linear model is limited by its features. Unlike a deep model, a generalized linear model cannot "learn new features. A system to create new data in which a generator creates data and a discriminator determines whether that created data is valid or invalid.

A generative model can theoretically discern the distribution of examples or particular features in a data set. The subsystem within a generative adversarial network that creates new examples. The vector of partial derivatives with respect to all of the independent variables. In machine learning, the gradient is the vector of partial derivatives of the model function. The gradient points in the direction of steepest ascent. Capping gradient values before applying them.

Gradient clipping helps ensure numerical stability and prevents exploding gradients. A technique to minimize loss by computing the gradients of loss with respect to the model's parameters, conditioned on training data. Informally, gradient descent iteratively adjusts parameters, gradually finding the best combination of weights and bias to minimize loss.

In TensorFlow, a computation specification. Nodes in the graph represent operations. Edges are directed and represent passing the result of an operation a Tensor as an operand to another operation. Use TensorBoard to visualize a graph. A TensorFlow programming environment in which the program first constructs a graph and then executes all or part of that graph.

Graph execution is the default execution mode in TensorFlow 1. Assuming that what is true for an individual is also true for everyone in that group. The effects of group attribution bias can be exacerbated if a convenience sample is used for data collection. In a non-representative sample, attributions may be made that do not reflect reality. See also out-group homogeneity bias and in-group bias. A practical and nonoptimal solution to a problem, which is sufficient for making progress or for learning from.

A synthetic layer in a neural network between the input layer that is, the features and the output layer the prediction. Hidden layers typically contain an activation function such as ReLU for training. A deep neural network contains more than one hidden layer.

A category of clustering algorithms that create a tree of clusters. Hierarchical clustering is well-suited to hierarchical data, such as botanical taxonomies. There are two types of hierarchical clustering algorithms:.

A family of loss functions for classification designed to find the decision boundary as distant as possible from each training example, thus maximizing the margin between examples and the boundary. KSVMs use hinge loss or a related function, such as squared hinge loss. For binary classification, the hinge loss function is defined as follows:.

Examples intentionally not used "held out" during training. The validation data set and test data set are examples of holdout data. Holdout data helps evaluate your model's ability to generalize to data other than the data it was trained on. The loss on the holdout set provides a better estimate of the loss on an unseen data set than does the loss on the training set. The "knobs" that you tweak during successive runs of training a model.

For example, learning rate is a hyperparameter. A boundary that separates a space into two subspaces. For example, a line is a hyperplane in two dimensions and a plane is a hyperplane in three dimensions. More typically in machine learning, a hyperplane is the boundary separating a high-dimensional space. Kernel Support Vector Machines use hyperplanes to separate positive classes from negative classes, often in a very high-dimensional space.

Implicit bias can affect the following:. For example, when building a classifier to identify wedding photos, an engineer may use the presence of a white dress in a photo as a feature. However, white dresses have been customary only during certain eras and in certain cultures. Data drawn from a distribution that doesn't change, and where each value drawn doesn't depend on values that have been drawn previously.

For example, the distribution of visitors to a web page may be i. However, if you expand that window of time, seasonal differences in the web page's visitors may appear. In machine learning, often refers to the process of making predictions by applying the trained model to unlabeled examples.

In statistics, inference refers to the process of fitting the parameters of a distribution conditioned on some observed data. See the Wikipedia article on statistical inference. Showing partiality to one's own group or own characteristics. If testers or raters consist of the machine learning developer's friends, family, or colleagues, then in-group bias may invalidate product testing or the data set.

In-group bias is a form of group attribution bias. See also out-group homogeneity bias. In TensorFlow, a function that returns input data to the training, evaluation, or prediction method of an Estimator.

For example, the training input function returns a batch of features and labels from the training set. The first layer the one that receives the input data in a neural network. The degree to which a model's predictions can be readily explained. Deep models are often non-interpretable; that is, a deep model's different layers can be hard to decipher.

By contrast, linear regression models and wide models are typically far more interpretable. A measurement of how often human raters agree when doing a task. If raters disagree, the task instructions may need to be improved. Also sometimes called inter-annotator agreement or inter-rater reliability. See also Cohen's kappa , which is one of the most popular inter-rater agreement measurements. In recommendation systems , a matrix of embeddings generated by matrix factorization that holds latent signals about each item.

Each row of the item matrix holds the value of a single latent feature for all items. For example, consider a movie recommendation system. Each column in the item matrix represents a single movie.

The latent signals might represent genres, or might be harder-to-interpret signals that involve complex interactions among genre, stars, movie age, or other factors. The item matrix has the same number of columns as the target matrix that is being factorized. For example, given a movie recommendation system that evaluates 10, movie titles, the item matrix will have 10, columns. In a recommendation system , the entities that a system recommends.

For example, videos are the items that a video store recommends, while books are the items that a bookstore recommends. A single update of a model's weights during training. An iteration consists of computing the gradients of the parameters with respect to the loss on a single batch of data.

A popular clustering algorithm that groups examples in unsupervised learning. The k-means algorithm basically does the following:. The k-means algorithm picks centroid locations to minimize the cumulative square of the distances from each example to its closest centroid.

Each example is assigned to its closest centroid, yielding three groups:. Imagine that a manufacturer wants to determine the ideal sizes for small, medium, and large sweaters for dogs. The three centroids identify the mean height and mean width of each dog in that cluster. So, the manufacturer should probably base sweater sizes on those three centroids. Note that the centroid of a cluster is typically not an example in the cluster. The preceding illustrations shows k-means for examples with only two features height and width.

Note that k-means can group examples across many features. A clustering algorithm closely related to k-means. The practical difference between the two is as follows:. A popular Python machine learning API.

Keras runs on several deep learning frameworks, including TensorFlow, where it is made available as tf. A classification algorithm that seeks to maximize the margin between positive and negative classes by mapping input data vectors to a higher dimensional space. For example, consider a classification problem in which the input data set consists of a hundred features.

In order to maximize the margin between positive and negative classes, KSVMs could internally map those features into a million-dimension space. KSVMs uses a loss function called hinge loss. Loss function based on the absolute value of the difference between the values that a model is predicting and the actual values of the labels.

L 1 loss is less sensitive to outliers than L 2 loss. A type of regularization that penalizes weights in proportion to the sum of the absolute values of the weights.

In models relying on sparse features , L 1 regularization helps drive the weights of irrelevant or barely relevant features to exactly 0, which removes those features from the model. Contrast with L 2 regularization. A type of regularization that penalizes weights in proportion to the sum of the squares of the weights.

L 2 regularization helps drive outlier weights those with high positive or low negative values closer to 0 but not quite to 0. Contrast with L1 regularization. L 2 regularization always improves generalization in linear models.

In supervised learning, the "answer" or "result" portion of an example. Each example in a labeled data set consists of one or more features and a label. For instance, in a housing data set, the features might include the number of bedrooms, the number of bathrooms, and the age of the house, while the label might be the house's price.

In a spam detection dataset, the features might include the subject line, the sender, and the email message itself, while the label would probably be either "spam" or "not spam. An example that contains features and a label. In supervised training, models learn from labeled examples.

This is an overloaded term. Here we're focusing on the term's definition within regularization. A set of neurons in a neural network that process a set of input features, or the output of those neurons.

Also, an abstraction in TensorFlow. Layers are Python functions that take Tensors and configuration options as input and produce other tensors as output. Once the necessary Tensors have been composed, the user can convert the result into an Estimator via a model function. The Layers API enables you to build different types of layers , such as:. When writing a custom Estimator , you compose Layers objects to define the characteristics of all the hidden layers.

That is, aside from a different prefix, all functions in the Layers API have the same names and signatures as their counterparts in the Keras layers API. A scalar used to train a model via gradient descent. During each iteration, the gradient descent algorithm multiplies the learning rate by the gradient.

The resulting product is called the gradient step. A linear regression model trained by minimizing L 2 Loss. A type of regression model that outputs a continuous value from a linear combination of input features.

A model that generates a probability for each possible discrete label value in classification problems by applying a sigmoid function to a linear prediction. Although logistic regression is often used in binary classification problems, it can also be used in multi-class classification problems where it becomes called multi-class logistic regression or multinomial regression.

The vector of raw non-normalized predictions that a classification model generates, which is ordinarily then passed to a normalization function. If the model is solving a multi-class classification problem, logits typically become an input to the softmax function. The softmax function then generates a vector of normalized probabilities with one value for each possible class.

In addition, logits sometimes refer to the element-wise inverse of the sigmoid function. For more information, see tf. The loss function used in binary logistic regression.

If the event refers to a binary probability, then odds refers to the ratio of the probability of success p to the probability of failure 1-p. In this case, odds is calculated as follows:. The log-odds is simply the logarithm of the odds. By convention, "logarithm" refers to natural logarithm, but logarithm could actually be any base greater than 1. Sticking to convention, the log-odds of our example is therefore:.

The log-odds are the inverse of the sigmoid function. A measure of how far a model's predictions are from its label. Or, to phrase it more pessimistically, a measure of how bad the model is. To determine this value, a model must define a loss function. For example, linear regression models typically use mean squared error for a loss function, while logistic regression models use Log Loss.

A graph of loss as a function of training iterations. The loss curve can help you determine when your model is converging , overfitting , or underfitting. A graph of weight s vs. Gradient descent aims to find the weight s for which the loss surface is at a local minimum. A program or system that builds trains a predictive model from input data. The system uses the learned model to make useful predictions from new never-before-seen data drawn from the same distribution as the one used to train the model.

Machine learning also refers to the field of study concerned with these programs or systems. The more common label in a class-imbalanced data set.

In recommendation systems , the target matrix often holds users' ratings on items. For example, the target matrix for a movie recommendation system might look something like the following, where the positive integers are user ratings and 0 means that the user didn't rate the movie:.

The movie recommendation system aims to predict user ratings for unrated movies. For example, will User 1 like Black Panther? One approach for recommendation systems is to use matrix factorization to generate the following two matrices:. For example, using matrix factorization on our three users and five items could yield the following user matrix and item matrix:. The dot product of the user matrix and item matrix yields a recommendation matrix that contains not only the original user ratings but also predictions for the movies that each user hasn't seen.

For example, consider User 1's rating of Casablanca , which was 5. The dot product corresponding to that cell in the recommendation matrix should hopefully be around 5. More importantly, will User 1 like Black Panther? Taking the dot product corresponding to the first row and the third column yields a predicted rating of 4. Matrix factorization typically yields a user matrix and item matrix that, together, are significantly more compact than the target matrix.

The average squared loss per example. MSE is calculated by dividing the squared loss by the number of examples. A number that you care about. May or may not be directly optimized in a machine-learning system. A metric that your system tries to optimize is called an objective. When writing a custom Estimator , you invoke Metrics API functions to specify how your model should be evaluated.

A small, randomly selected subset of the entire batch of examples run together in a single iteration of training or inference. The batch size of a mini-batch is usually between 10 and 1, It is much more efficient to calculate the loss on a mini-batch than on the full training data. A gradient descent algorithm that uses mini-batches. In other words, mini-batch SGD estimates the gradient based on a small subset of the training data.

Vanilla SGD uses a mini-batch of size 1. The less common label in a class-imbalanced data set. A public-domain data set compiled by LeCun, Cortes, and Burges containing 60, images, each image showing how a human manually wrote a particular digit from 0—9. Each image is stored as a 28x28 array of integers, where each integer is a grayscale value between 0 and , inclusive. The representation of what an ML system has learned from the training data. Within TensorFlow, model is an overloaded term, which can have either of the following two related meanings:.

The function within an Estimator that implements ML training, evaluation, and inference. For example, the training portion of a model function might handle tasks such as defining the topology of a deep neural network and identifying its optimizer function.

When using premade Estimators , someone has already written the model function for you. When using custom Estimators , you must write the model function yourself. For details about writing a model function, see Creating Custom Estimators. A sophisticated gradient descent algorithm in which a learning step depends not only on the derivative in the current step, but also on the derivatives of the step s that immediately preceded it.

Momentum involves computing an exponentially weighted moving average of the gradients over time, analogous to momentum in physics. Momentum sometimes prevents learning from getting stuck in local minima. Classification problems that distinguish among more than two classes.

For example, there are approximately species of maple trees, so a model that categorized maple tree species would be multi-class. Conversely, a model that divided emails into only two categories spam and not spam would be a binary classification model.

When one number in your model becomes a NaN during training, which causes many or all other numbers in your model to eventually become a NaN. Determining a user's intentions based on what the user typed or said. For example, a search engine uses natural language understanding to determine what the user is searching for based on what the user typed or said.

In binary classification , one class is termed positive and the other is termed negative. The positive class is the thing we're looking for and the negative class is the other possibility. For example, the negative class in a medical test might be "not tumor. A model that, taking inspiration from the brain, is composed of layers at least one of which is hidden consisting of simple connected units or neurons followed by nonlinearities.

A node in a neural network , typically taking in multiple input values and generating one output value. The neuron calculates the output value by applying an activation function nonlinear transformation to a weighted sum of input values. An ordered sequence of N words. For example, truly madly is a 2-gram. Because order is relevant, madly truly is a different 2-gram than truly madly.

Many natural language understanding models rely on N-grams to predict the next word that the user will type or say. For example, suppose a user typed three blind. An NLU model based on trigrams would likely predict that the user will next type mice. Contrast N-grams with bag of words , which are unordered sets of words. Abbreviation for natural language understanding. A neuron in a hidden layer. Broadly speaking, anything that obscures the signal in a data set. Noise can be introduced into data in a variety of ways.

For example, suppose the natural range of a certain feature is to 6, Features represented as integers or real-valued numbers. For example, in a real estate model, you would probably represent the size of a house in square feet or square meters as numerical data.

Pooling usually involves taking either the maximum or average value across the pooled area.

The prototypical convex function is shaped something like the letter U.