they do not know enough about the topic at hand or because, they say, theysimply are not “smart enough.”

BLEND THE AUTHOR’S WORDS WITH YOUR OWN

VERBS FOR MAKING A CLAIM

his ability to enter complex, many-sided conversations has taken on aspecial urgency in today’s polarized red state / blue state America,

Letter from Birmingham Jail,

f you have been taught to write atraditional five-paragraph essay, for example, you have learned how todevelop a thesis and support it with evidence.

Less experiencedwriters, by contrast, are often unfamiliar with these basic moves and unsurehow to make them in their own writing.

STATE YOUR OWN IDEAS AS A RESPONSE TOOTHERS

once you mastered it you no longerhad to give much conscious thought to the various moves that go into doingit.

“Why don’tyou do something about it?’

for their knowledge of theirown ignorance.

The father was a quiet, simple soul, calmly ignorant, with no touch of vulgarity. The mother wasdifferent,—strong, bustling, and energetic, with a quick, restless tongue, and an ambition to live“like folks.”

it is easier to do ill than well in the world

We use the same model and architecture as GPT-2

Now we are getting somewhere. At this point, we also see that the dimensions of W and b for each layer are specified by the dimensions of the inputs and the number of nodes in each layer. Let’s clean up the above diagram by not labeling every w and b value individually.

The Delta Method, from the field of nonlinear regression. The Bayesian Method, from Bayesian modeling and statistics. The Mean-Variance Estimation Method, using estimated statistics. The Bootstrap Method, using data resampling and developing an ensemble of models.

A novel method for estimating prediction uncertainty using machine learning techniques is presented. Uncertainty is expressed in the form of the two quantiles (constituting the prediction interval) of the underlying distribution of prediction errors. The idea is to partition the input space into different zones or clusters having similar model errors using fuzzy c-means clustering. The prediction interval is constructed for each cluster on the basis of empirical distributions of the errors associated with all instances belonging to the cluster under consideration and propagated from each cluster to the examples according to their membership grades in each cluster. Then a regression model is built for in-sample data using computed prediction limits as targets, and finally, this model is applied to estimate the prediction intervals (limits) for out-of-sample data. The method was tested on artificial and real hydrologic data sets using various machine learning techniques. Preliminary results show that the method is superior to other methods estimating the prediction interval. A new method for evaluating performance for estimating prediction interval is proposed as well.

the Elhage et al.(2021) study showing an information-copying role for self-attention.

This input embedding is the initial value of the residual stream, which all attention layers and MLPs read from and write to.

e twoareas in which the forward-forward algorithm may be superior to backpropagation are as a model oflearning in cortex and as a way of making use of very low-power analog hardware without resortingto reinforcement learning(Jabri and Flower, 1992).

Our method is based on the hypothesis that the weights of a generator act as Optimal Linear Associative Memory (OLAM). OLAM is a classic single-layer neural data structure for memorizing associations that was described by Teuvo Kohonen and James A Anderson (independently) in the 1970s. In our case, we hypothesize that within a large modern multilayer convolutional network, the each individual layer plays the role of an OLAM that stores a set of rules that associates keys, which denote meaningful context, with values, which determine output.

OCaml 语言能做些什么？

AI training data is filled with racist stereotypes, pornography, and explicit images of rape, researchers Abeba Birhane, Vinay Uday Prabhu, and Emmanuel Kahembwe found after analyzing a data set similar to the one used to build Stable Diffusion.

We test this hypothesis by training a predicted compute-optimal model, Chinchilla, that uses the same compute budget as Gopher but with 70B parameters and4× more more data. Chinchilla uniformly and significantly outperforms Gopher (280B), GPT-3 (175B),Jurassic-1 (178B), and Megatron-Turing NLG (530B) on a large range of downstream evaluation tasks.This also means that Chinchilla uses substantially less compute for fine-tuning and inference, greatlyfacilitating downstream usage. As a highlight, Chinchilla reaches a state-of-the-art average accuracy of67.5% on the MMLU benchmark, greater than a 7% improvement over Gopher

Kuratierungs-Filter auf Empfängerseite gibt, aber dann wäre auch e-mail-Spam als Problem gelöst und das sehe ich gerade noch nicht passieren.

🌟 Highlight words as they are spoken (karaoke anybody?). 🌟 Navigate video by clicking on words. 🌟 Share snippets of text (with video attached!). 🌟 Repurpose by remixing using the text as a base and reference.

“The metaphor is that the machine understands what I’m saying and so I’m going to interpret the machine’s responses in that context.”

Scaling PostgresML to 1 Million Requests per Second

Consider a toy model where we train an embedding of five features of varying importanceWhere “importance” is a scalar multiplier on mean squared error loss. in two dimensions, add a ReLU afterwards for filtering, and vary the sparsity of the features.

The present generation of Southerners are not responsible for the past

Haytian revolt

his educational programme was un-necessarily narrow.

the Free Negroes from 1830 up to war-time hadstriven to build industrial schools, and the American Missionary Associ-ation had from the first taught various trades; and Price and others hadsought a way of honorable alliance with the best of the Southerners. ButMr. Washington first indissolubly linked these things; he put enthusiasm,unlimited energy, and perfect faith into his programme, and changed itfrom a by-path into a veritable Way of Life

Our schools teach everybody a little of almosteverything, but, in my opinion, they teach very fewchildren just what they ought to know in order tomake their way successfully in life. They do not putinto their hands the tools they are best tted to use,and hence so many failures. Many a mother andsister have worked and slaved, living upon scantyfood, in order to give a son and brother a ’liberaleducation,’ and in doing this have built up a barrierbetween the boy and the work he was tted to do.Let me say to you that all honest work is honorablework. If the labor is manual, and seems common,you will have all the more chance to be thinking ofother things, or of work that is higher and bringsbetter pay, and to work out in your minds betterand higher duties and responsibilities foryourselves, and for thinking of ways by which youcan help others as well as yourselves, and bringthem up to your own higher level.

Our schools teach everybody a little of almosteverything, but, in my opinion, they teach very fewchildren just what they ought to know in order tomake their way successfully in life. They do not putinto their hands the tools they are best tted to use,and hence so many failures. Many a mother andsister have worked and slaved, living upon scantyfood, in order to give a son and brother a ’liberaleducation,’ and in doing this have built up a barrierbetween the boy and the work he was tted to do.Let me say to you that all honest work is honorablework. If the labor is manual, and seems common,you will have all the more chance to be thinking ofother things, or of work that is higher and bringsbetter pay, and to work out in your minds betterand higher duties and responsibilities foryourselves, and for thinking of ways by which youcan help others as well as yourselves, and bringthem up to your own higher level.

Our schools teach everybody a little of almosteverything, but, in my opinion, they teach very fewchildren just what they ought to know in order tomake their way successfully in life.

“Our schools teach everybody a little of almosteverything, but, in my opinion, they teach very fewchildren just what they ought to know in order tomake their way successfully in life.

Uncle Bird had a small, rough farm, all woods and hills, miles from the big road; but he was fullof tales

willow

Now, the progression of NLP, as discussed, tells a story. We begin with tokens and then build representations of these tokens. We use these representations to find similarities between tokens and embed them in a high-dimensional space. The same embeddings are also passed into sequential models that can process sequential data. Those models are used to build context and, through an ingenious way, attend to parts of the input sentence that are useful to the output sentence in translation.

Data, matrix multiplications, repeated and scaled with non-linear switches. Maybe that simplifies things a lot, but even today, most architectures boil down to these principles. Even the most complex systems, ideas, and papers can be boiled down to just that:

Summarization of Methods for Smart Contract Vulnerabilities Detection

graphs

Z-code models to improve common language understanding tasks such as name entity recognition, text summarization, custom text classification and key phrase extraction across its Azure AI services. But this is the first time a company has publicly demonstrated that it can use this new class of Mixture of Experts models to power machine translation products.

have developed called Z-code, which offer the kind of performance and quality benefits that other large-scale language models have but can be run much more efficiently.

The dominant idea is one of attention, by which a representation at a position is computed as a weighted combination of representations from other positions. A common self-supervision objective in a transformer model is to mask out occasional words in a text. The model works out what word used to be there. It does this by calculating from each word position (including mask positions) vectors that represent a query, key, and value at that position. The query at a position is compared with the value at every position to calculate how much attention to pay to each position; based on this, a weighted average of the values at all positions is calculated. This operation is repeated many times at each level of the transformer neural net, and the resulting value is further manipulated through a fully connected neural net layer and through use of normalization layers and residual connections to produce a new vector for each word. This whole process is repeated many times, giving extra layers of depth to the transformer neural net. At the end, the representation above a mask position should capture the word that was there in the original text: for instance, committee as illustrated in Figure 1.

This trick of using a one-hot vector to pull out a particular row of a matrix is at the core of how transformers work.

Given the complexities of the brain’s structure and the functions it performs, any one of these models is surely oversimplified and ultimately wrong—at best, an approximation of some aspects of what the brain does. However, some models are less wrong than others, and consistent trends in performance across models can reveal not just which model best fits the brain but also which properties of a model underlie its fit to the brain, thus yielding critical insights that transcend what any single model can tell us.

Such a highly non-linear problem would clearly benefitfrom the computational power of many layers. Unfortu-nately, back-propagation learning generally slows downby an order of magnitude every time a layer is added toa network.

The source sequence will be pass to the TransformerEncoder, which will produce a new representation of it. This new representation will then be passed to the TransformerDecoder, together with the target sequence so far (target words 0 to N). The TransformerDecoder will then seek to predict the next words in the target sequence (N+1 and beyond).

Ourpre-trained network is nearly identical to the “AlexNet”architecture (Krizhevsky et al., 2012), but with local re-ponse normalization layers after pooling layers following(Jia et al., 2014). It was trained with the Caffe frameworkon the ImageNet 2012 dataset (Deng et al., 2009)

Example 1. For example, suppose that the input volume has size [32x32x3], (e.g. an RGB CIFAR-10 image). If the receptive field (or the filter size) is 5x5, then each neuron in the Conv Layer will have weights to a [5x5x3] region in the input volume, for a total of 5*5*3 = 75 weights (and +1 bias parameter). Notice that the extent of the connectivity along the depth axis must be 3, since this is the depth of the input volume. Example 2. Suppose an input volume had size [16x16x20]. Then using an example receptive field size of 3x3, every neuron in the Conv Layer would now have a total of 3*3*20 = 180 connections to the input volume. Notice that, again, the connectivity is local in 2D space (e.g. 3x3), but full along the input depth (20).

input (32x32x3)max activation: 0.5, min: -0.5max gradient: 1.08696, min: -1.53051Activations:Activation Gradients:Weights:Weight Gradients:conv (32x32x16)filter size 5x5x3, stride 1max activation: 3.75919, min: -4.48241max gradient: 0.36571, min: -0.33032parameters: 16x5x5x3+16 = 1216

Here the lower level layers are frozen and are not trained, only the new classification head will update itself to learn from the features provided from the pre-trained chopped up model on the left.

Starting from random noise, we optimize an image to activate a particular neuron (layer mixed4a, unit 11).

A special quality of humans, not shared by evolution or, as yet, by machines, is our ability to recognize gaps in our understanding and to take joy in the process of filling them in. It is a beautiful thing to experience the mysterious, and powerful, too.

Verfahren des Relational Machine Learning, welche unter Ausnutzung der Graphstruktur in vielen Fällen Modelle besserer Qualität liefern.

In vielen Anwendungen ist es allerdings notwendig, Daten nicht nur in hoher Qualität und semantisch angereichert zur Verfügung zu stellen, sondern neues Wissen aus vorhandenen Informationen zu generieren. Hierfür nutzen wir Machine Learning.

Somewhat confusingly, and for historical reasons, such multiple layer networks are sometimes called multilayer perceptrons or MLPs, despite being made up of sigmoid neurons, not perceptrons. I'm not going to use the MLP terminology in this book, since I think it's confusing, but wanted to warn you of its existence.

the only thing an artificial neuron can do: classify a data point into one of two kinds by examining input values with weights and bias.

The transformer model introduces the idea of instead of adding another complex mechanism (attention) to an already complex Seq2Seq model; we can simplify the solution by forgetting about everything else and just focusing on attention.

I’m particularly interested in two questions: First, just how weird is machine learning? Second, what sorts of choices do developers make as they shape a project?

ey use local computations to interpolate over task-rele-vant manifolds in a high-dimensional parameter space.

Now that we've made peace with the concepts of projections (matrix multiplications)

Computers are especially good at matrix multiplications. There is an entire industry around building computer hardware specifically for fast matrix multiplications. Any computation that can be expressed as a matrix multiplication can be made shockingly efficient.

The selective-second-order-with-skips model is a useful way to think about what transformers do, at least in the decoder side. It captures, to a first approximation, what generative language models like OpenAI's GPT-3 are doing.

You'll use a (70%, 20%, 10%) split for the training, validation, and test sets. Note the data is not being randomly shuffled before splitting. This is for two reasons: It ensures that chopping the data into windows of consecutive samples is still possible. It ensures that the validation/test results are more realistic, being evaluated on the data collected after the model was trained.

The following figure presents a simple functional diagram of the neural network we will use throughout the article. The neural network is a sequence of linear (both convolutional A convolution calculates weighted sums of regions in the input. In neural networks, the learnable weights in convolutional layers are referred to as the kernel. For example Image credit to https://towardsdatascience.com/gentle-dive-into-math-behind-convolutional-neural-networks-79a07dd44cf9. See also Convolution arithmetic. and fully-connected A fully-connected layer computes output neurons as weighted sum of input neurons. In matrix form, it is a matrix that linearly transforms the input vector into the output vector. ), max-pooling, and ReLU First introduced by Nair and Hinton, ReLU calculates f(x)=max(0,x)f(x)=max(0,x)f(x)=max(0,x) for each entry in a vector input. Graphically, it is a hinge at the origin: Image credit to https://pytorch.org/docs/stable/nn.html#relu layers, culminating in a softmax Softmax function calculates S(yi)=eyiΣj=1NeyjS(y_i)=\frac{e^{y_i}}{\Sigma_{j=1}^{N} e^{y_j}}S(yi​)=Σj=1N​eyj​eyi​​ for each entry (yiy_iyi​) in a vector input (yyy). For example, Image credit to https://ljvmiranda921.github.io/notebook/2017/08/13/softmax-and-the-negative-log-likelihood/ layer.

The Query word can be interpreted as the word for which we are calculating Attention. The Key and Value word is the word to which we are paying attention ie. how relevant is that word to the Query word.

Other work on interpreting transformer internals has focused mostly on what the attention is looking at. The logit lens focuses on what GPT "believes" after each step of processing, rather than how it updates that belief inside the step.

The cube of activations that a neural network for computer vision develops at each hidden layer. Different slices of the cube allow us to target the activations of individual neurons, spatial positions, or channels.

The attention layer (W in the diagram) computes three vectors based on the input, termed key, query, and value.

Attention is a means of selectively weighting different elements in input data, so that they will have an adjusted impact on the hidden states of downstream layers.

These findings provide strong evidence for a classic hypothesis about the computations underlying human language understanding, that the brain’s language system is optimized for predictive processing in the service of meaning extraction

To review, the Forget gate decides what is relevant to keep from prior steps. The input gate decides what information is relevant to add from the current step. The output gate determines what the next hidden state should be.Code DemoFor those of you who understand better through seeing the code, here is an example using python pseudo code.

This approach, visualizing high-dimensional representations using dimensionality reduction, is an extremely broadly applicable technique for inspecting models in deep learning.

These layers warp and reshape the data to make it easier to classify.

Even with this very primitive single neuron, you can achieve 90% accuracy when recognizing a handwritten text image1. To recognize all the digits from 0 to 9, you would need just ten neurons to recognize them with 92% accuracy.

Humans perform a version of this task when interpretinghard-to-understand speech, such as an accent which is particularlyfast or slurred, or a sentence in a language we do not know verywell—we do not necessarily hear every single word that is said,but we pick up on salient key words and contextualize the rest tounderstand the sentence.

A neural network will predict your digit in the blue square above. Your image is 784 pixels (= 28 rows by 28 columns with black=1 and white=0). Those 784 features get fed into a 3 layer neural network; Input:784 - AvgPool:196 - Dense:100 - Softmax:10.

Personalized ASR models. For each of the 432 participants with disordered speech, we create a personalized ASR model (SI-2) from their own recordings. Our fine-tuning procedure was optimized for our adaptation process, where we only have between ¼ and 2 h of data per speaker. We found that updating only the first five encoder layers (versus the complete model) worked best and successfully prevented overfitting [10]

So whenever you hear of someone “training” a neural network, it just means finding the weights we use to calculate the prediction.

I'm going to try provide an English text example. The following is based solely on my intuitive understanding of the paper 'Attention is all you need'.

For the word q that your eyes see in the given sentence, what is the most related word k in the sentence to understand what q is about?

So basically: q = the vector representing a word K and V = your memory, thus all the words that have been generated before. Note that K and V can be the same (but don't have to). So what you do with attention is that you take your current query (word in most cases) and look in your memory for similar keys. To come up with a distribution of relevant words, the softmax function is then used.

A neural network with a hidden layer has universality: given enough hidden units, it can approximate any function. This is a frequently quoted – and even more frequently, misunderstood and applied – theorem. It’s true, essentially, because the hidden layer can be used as a lookup table.

Recursive Neural Networks

The second-to-last layer is what Han settled on as a reasonable sweet-spot.

We show that BigBird is a universal approximator of sequence functions and is Turing complete,

hyper-parameters, i.e., parameters external to the model, such as the learning rate, the batch size, the number of epochs.

In the language of Interpretable Machine Learning (IML) literature like Molnar et al.[20], input saliency is a method that explains individual predictions.

Vectors with a small Euclidean distance from one another are located in the same region of a vector space. Vectors with a high cosine similarity are located in the same general direction from the origin.

If you're serious about neural networks, I have one recommendation. Try to rebuild this network from memory.

If you're serious about neural networks, I have one recommendation. Try to rebuild this network from memory.

In our research, i.e., the wormnet project, we try to build machine learning models motivated by the C. elegans nervous system. By doing so, we have to pay a cost, as we constrain ourselves to such models in contrast to standard artificial neural networks, whose modeling space is purely constraint by memory and compute limitations. However, there are potentially some advantages and benefits we gain. Our objective is to better understand what’s necessary for effective neural information processing to emerge.

Recommendations DON'T use shifted PPMI with SVD. DON'T use SVD "correctly", i.e. without eigenvector weighting (performance drops 15 points compared to with eigenvalue weighting with (p = 0.5)). DO use PPMI and SVD with short contexts (window size of (2)). DO use many negative samples with SGNS. DO always use context distribution smoothing (raise unigram distribution to the power of (lpha = 0.75)) for all methods. DO use SGNS as a baseline (robust, fast and cheap to train). DO try adding context vectors in SGNS and GloVe.

2D Vectors in space. Image by Author

One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with increased computation even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are search and learning

"dividing n-dimensional space with a hyperplane."

This dataset can not be classified by a single neuron, as the two groups of data points can't be divided by a single line.

Machine learning is an extension of linear regression in a few ways. Firstly is that modern ML

survival prediction of colorectal cancer is formulated as a multi-class classification problem

可以认为 π k \pi_k πk​就是每个分量 N ( x ∣ μ k , Σ k ) \mathcal{N}(\boldsymbol{x}|\boldsymbol{\mu}_k, \boldsymbol{\Sigma}_k) N(x∣μk​,Σk​)的权重。

LEGO

Data Augmentation

Machine learning has a limited scope

AI is a bigger concept to create intelligent machines that can simulate human thinking capability and behavior, whereas, machine learning is an application or subset of AI that allows machines to learn from data without being programmed explicitly

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. Use Keras if you need a deep learning library that: Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility). Supports both convolutional networks and recurrent networks, as well as combinations of the two. Runs seamlessly on CPU and GPU. Read the documentation at Keras.io. Keras is compatible with: Python 2.7-3.6.

Suppose the algorithm chooses a tree that splits on education but not on age. Conditional on this tree, the estimated coefficients are consistent. But that does not imply that treatment effects do not also vary by age, as education may well covary with age; on other draws of the data, in fact, the same procedure could have chosen a tree that split on age instead

hese heterogenous treatment effects can be used to assign treatments; Misra and Dubé (2016) illustrate this on the problem of price targeting, applying Bayesian regularized methods to a large-scale experiment where prices were randomly assigned

Chernozhukov, Chetverikov, Demirer, Duflo, Hansen, and Newey (2016) take care of high-dimensional controls in treatment effect estimation by solving two simultaneous prediction problems, one in the outcome and one in the treatment equation.

These same techniques applied here result in split-sample instrumental variables (Angrist and Krueger 1995) and “jackknife” instrumental variables

Understood this way, the finite-sample biases in instrumental variables are a consequence of overfitting.

Even when we are interested in a parameter β ˆ, the tool we use to recover that parameter may contain (often implicitly) a prediction component. Take the case of linear instrumental variables understood as a two-stage procedure: first regress x = γ′z + δ on the instrument z, then regress y = β′x + ε on the fitted values x ˆ. The first stage is typically handled as an estimation step. But this is effectively a prediction task: only the predictions x ˆ enter the second stage; the coefficients in the first stage are merely a means to these fitted values.

Prediction in the Service of Estimation

New Data

Zhao and Yu (2006) who establish asymptotic model-selection consistency for the LASSO. Besides assuming that the true model is “sparse”—only a few variables are relevant—they also require the “irrepresentable condition” between observables: loosely put, none of the irrelevant covariates can be even moderately related to the set of relevant ones.

First, it encourages the choice of less complex, but wrong models. Even if the best model uses interactions of number of bathrooms with number of rooms, regularization may lead to a choice of a simpler (but worse) model that uses only number of fireplaces. Second, it can bring with it a cousin of omitted variable bias, where we are typically concerned with correlations between observed variables and unobserved ones. Here, when regular-ization excludes some variables, even a correlation between observed variables and other observed (but excluded) ones can create bias in the estimated coefficients.

97the variables are correlated with each other (say the number of rooms of a house and its square-footage), then such variables are substitutes in predicting house prices. Similar predictions can be produced using very different variables. Which variables are actually chosen depends on the specific finite sample.

Through its regularizer, LASSO produces a sparse prediction function, so that many coefficients are zero and are “not used”—in this example, we find that more than half the variables are unused in each run

One obvious problem that arises in making such inferences is the lack of stan-dard errors on the coefficients. Even when machine-learning predictors produce familiar output like linear functions, forming these standard errors can be more complicated than seems at first glance as they would have to account for the model selection itself. In fact, Leeb and Pötscher (2006, 2008) develop conditions under which it is impossible to obtain (uniformly) consistent estimates of the distribution of model parameters after data-driven selection.

First, econometrics can guide design choices, such as the number of folds or the function class.

These choices about how to represent the features will interact with the regularizer and function class: A linear model can reproduce the log base area per room from log base area and log room number easily, while a regression tree would require many splits to do so.

Ta b l e 2Some Machine Learning Algorithms

Picking the prediction func-tion then involves two steps: The first step is, conditional on a level of complexity, to pick the best in-sample loss-minimizing function.8 The second step is to estimate the optimal level of complexity using empirical tuning (as we saw in cross-validating the depth of the tree).

egularization combines with the observability of predic-tion quality to allow us to fit flexible functional forms and still find generalizable structure.

This procedure works because prediction quality is observable: both predic-tions y ˆ and outcomes y are observed. Contrast this with parameter estimation, where typically we must rely on assumptions about the data-generating process to ensure consistency.

In empirical tuning, we create an out-of-sample experiment inside the original sample.

Performance of Different Algorithms in Predicting House Values

We consider 10,000 randomly selected owner-occupied units from the 2011 metropolitan sample of the American Housing Survey. In addition to the values of each unit, we also include 150 variables that contain information about the unit and its location, such as the number of rooms, the base area, and the census region within the United States. To compare different prediction tech-niques, we evaluate how well each approach predicts (log) unit value on a separate hold-out set of 41,808 units from the same sample. All details on the sample and our empirical exercise can be found in an online appendix available with this paper athttp://e-jep.org

Making sense of complex data such as images and text often involves a prediction pre-processing step.

The fundamental insight behind these breakthroughs is as much statis-tical as computational. Machine intelligence became possible once researchers stopped approaching intelligence tasks procedurally and began tackling them empirically.

In another category of applications, the key object of interest is actually a parameter β, but the inference procedures (often implicitly) contain a prediction task. For example, the first stage of a linear instrumental variables regres-sion is effectively prediction. The same is true when estimating heterogeneous treatment effects, testing for effects on multiple outcomes in experiments, and flexibly controlling for observed confounders.

Machine Learning: An Applied Econometric Approach