greetings

a type of house

silent

a type of clothing

used to emphasize something

being near to unconcious

shook

gently push

clean something made of water

a deep hole made by water

to make a loud crunch

hurting another person

decorated with ornaments

medicinal twigs

relaxed and calm

looked for to get

arrogant and superior

periodic wind in the indian ocean

in a bad mood

showing respect

hum sentimentally

something like a clarinet

confused

another word for responded

worthless salary

to work hard and long

ready to fight

spread out

poked

smell

to balance unsteadily

laugh in a jokefull way

confident

move swiftly

very large robe

some big fruit

thread

pattern design.

species of wolf

to walk with effort

gently turning something over

serious

tent building material

with affection

to frown in anger

likely to collapse

crossing

it is a tool that presses things. This case it was pressing her shoulder

confused

stretched

to become compressed with dirt

laugh with hate

stuttering and being unconfident of what you are saying

wilted:become limp with heat or water, lost energy.

For a machine learning model to be trusted/ used one would need to be confident in its capabilities of dealing with all possible scenarios. To that end, designing unit test cases for more complex and global problems could be costly and bordering on impossible to create.

Idea: We need a basic guideline that researchers and developers can adhere to when defining problems and outlining solutions, so that model interpretability can be defined accurately in terms of the problem statement.

Solution: This paper outlines the basics of machine learning interpretability, what that means for different users, and how to classify these into understandable categories that can be evaluated. This paper highlights the need for interpretability, which arises from incompleteness,either of the problem statement, or the problem domain knowledge. This paper provides three main categories to evaluating a model/ providing interpretations:

• Application Grounded Evaluation: These evaluations are more costly, and involve real humans evaluating real tasks that a model would take up. Domain knowledge is necessary for the humans evaluating the real task handled by the model.
• Human Grounded Evaluation: these evaluations are simpler than application grounded, as they simplify the complex task and have humans evaluate the simplified task. Domain knowledge is not necessary in such an evaluation. (However such explanations can be skewed toward human trust as opposed to faithfulness to the model)
• Functionally Grounded Evaluation: No humans are involved in this version of evaluation, here previously evaluated models are perfected or tweaked to optimize certain functionality. Explanation quality is measured by a formal definition of interpretability.

This paper also outlines certain issues with the above three evaluation processes, there are certain questions that need answering before we can pick an evaluation method and metric. -To highlight the factors of interpretability, we are provided with the Data-driven approach. Here we analyze each task and the various methods used to fulfill the task and see which of these methods and tasks are most significant to the model.

• We are introduced to the term latent dimensions of interpretability, i.e. dimensions that are inferred not observed. These are divided into task related latent dimensions and method related latent dimensions, these are a long list of factors that are task specific or method specific.

Thus this paper provides a basic taxonomy for how we should evaluate our model, and how these evaluations differ from problem to problem. The ideal scenario outlined is that researchers provide the relevant information to evaluate their proposition correctly (correctly in terms of the domain and the problem scope).

With growing use of ML and AI solutions to complex problems, there is a rise in need for understanding and explaining these models appropriately however these explanations vary in how well they adhere to the model/ explain the decisions in a human understandable way.

Idea : There is no standard method of categorizing interpretation methods/ explanations, and no good working practices in the field of interpretability.

Solution : This paper explores and categorizes different approaches to interpreting machine learning models. The three main categories this paper proposes are:

• Processing: interpretation approach that uses surrogate models to explain complex models
• Representation: interpretation approach that analyzes intermediate data representations in models with transferability of data/ layers
• Explaining Producing: interpretation approach in which the trained model as part of it's processing also generates an explanation for its process.

In this paper we see different approaches to interpretation in detail, analyzing what the major component is to the interpretation, And which proposed category the explanation method would fall under. The paper goes into detail about other research papers that also deal with categorizing or exploring explanations, and the overall meaning of explainability in other domains.

This paper also touches on how "completeness" (defined as how close the explanation is to the underlying model) and "interpretation" (defined as how easily humans can understand/ trust the model) do have tradeoffs, the author argues that these tradeoffs not only exist in the final explanation, but within each category the definition of completeness would be different and the metric used to measure this would change, which makes sense when you think that different users have different viewpoints on how a model should behave, and what the desired explanation for a result is.

This approach seems similar to small interpretable ensembles, where we approximate the global interpretation from smaller local interpretations of a model.

Model interpretations must be true to the model but must also promote human understanding of the working of the model. To this end we would need an interpretability model that balances the two.

Idea : Although there exist model interpretations that balance fidelity and human cognition on a local level specific to an underlying model, there are no global model agnostic interpretation models that can achieve the same.

Solution:

• Break up each aspect of the underlying model into distinct compact decision sets that have no overlap to generate explanations that are faithful to the model, and also cover all possible feature spaces of the model.
• How the solution dealt with:
  • Fidelity (staying true to the model): the labels in the approximation match that of the underlying model.
  • Unambiguity (single clear decision): compact decision sets in every feature space ensures unambiguity in the label assigned to it.
  • Interpretability (Understandable by humans): Intuitive rule based representation, with limited number of rules and predicates.
  • Interactivity (Allow user to focus on specific feature spaces): Each feature space is divided into distinct compact sets, allowing users to focus on their area of interest.
• Details on a “decision set”:
  • Each decision set is a two-level decision (a nested if-then decision set), where the outer if-then clause specifies the sub-space, and the inner if-then clause specifies the logic of assigning a label by the model.
  • A default set is defined to assign labels that do not satisfy any of the two-level decisions
  • The pros of such a model is that we do not need to trace the logic of an assigned label too far, thus less complex than a decision tree which follows a similar if-then structure.

Mapping fidelity vs interpretability

• To see how their model handled fidelity vs interpretability, they mapped the rate of agreement (number of times the approximation label of an instance matches the blackbox assigned label) against pre-defined interpretability complexity defining terms such as:
  • Number of predicates (sum of width of all decision sets)
  • Number of rules (a set of outer decision, inner decision, and classifier label)
  • Number of defined neighborhoods (outer if-then decision)
• Their model reached higher agreement rates to other models at lower values for interpretability complexity.

Model Interpretability aims at explaining the inner workings of a model promoting transparency of any decisions made by the model, however for the sake of human acceptance or understanding, these explanations seem to be more geared toward human trust than remaining faithful to the model.

Idea There is a distinct difference and tradeoff between persuasive and descriptive Interpretations of a model, one promotes human trust while the other stays truthful to the model. Promoting the former can lead to a loss in transparency of the model.

Questions to be answered:

• How do we balance between a persuasive strategy and a descriptive strategy?
• How do we combat human cognitive bias?

Solutions:

• Separating the descriptive and persuasive steps:
  • We first generate a descriptive explanation, without trying to simplify it
  • In our final steps we add persuasiveness to this explanation to make it more understandable
• Explicit inclusion of cognitive features:
  • We would include attributes that affect our functional measures of interpretability to our objective function.
  • This approach has some drawbacks however:
    • we would need to map the knowledge of the user which is an expensive process.
    • Any features that we fail to add to the objective function would add to the human cognitive bias
    • Increased complexity in optimizing of a multi-objective loss function.

Important terms:

• Explanation Strategy: An explanation strategy is defined as an explanation vehicle coupled with the objective function, constraints, and hyper parameters required to generate a model explanation
• Explanation model: An explanation model is defined as the implementation of an explanation strategy, which is fit to a model that is to be interpreted.
• Human Cognitive Bias: if an explanation model is highly persuasive or tuned toward human trust as opposed to staying true to the model, the overall evaluation of this explanation would be highly biased compared to a descriptive model. This bias can lead from commonalities between human users across a domain, expertise of the application, or the expectation of a model explanation. Such bias is known as implicit human cognitive bias.
• Persuasive Explanation Strategy: A persuasive explanation strategy aim at convincing a user/ humanizing a model so that the user feels more comfortable with the decisions generated by the model. Fidelity or truthfulness to the model in such a strategy can be very low, which can lead to ethical dilemmas as to where to draw the line between being persuasive and being descriptive. Persuasive strategies do promote human understanding and cognition, which are important aspects of interpretability, however they fail to address the certain other aspects such as fidelity to the model.
• Descriptive Explanation Strategy: A descriptive explanation strategy stays true to the underlying model, and generates explanations with maximum fidelity to the model. Ideally such a strategy would describe exactly what the inner working of the underlying model is, which is the main purpose of model interpretation in terms of better understanding the actual workings of the model.

These two links are different, although the sites that they link to look similar.

These two P-Patches have almost the exact same name, but they're different -- I promise!

The Beacon Food Forest is especially cool, because (1) it's massive, and (2) it has such a massive variety of foods from all over the world. It's an ethnobotanist's dream garden!

Be aware -- the P&R trail-specific website is different from the general, park-related website.

Honestly, I would LOVE to trailer a horse out here and tramp around!

Burke-Gilman? . . . This will come up later, too . . .

The names of features which are included in this set of maps are color-coded to match the color used to represent the feature on the map!

My custom logo hyperlinks to my UW Canvas profile.

This collection is also useful for including the twitters of film societies and filmmakers.

This website résumé for filmmaker Christina Battle showcases her expansive filmography. It represents the diversity of websites within this collection. Compare this expansive and dense website with the focused and light interview with Cameron Macgowan http://calgaryisawesome.com/2013/10/25/profile-cameron-macgowan/

This is an illustrative portrait of one Calgary based filmmaker. It is an intimate article that not only highlights the individual, but also reveals the film-making scene in Calgary. Compare this focused and light piece to the expansive and dense website résumé cbattle.com.

Although it only includes news articles from immediately after the event, the collections of articles gives a look into reactions to the event, and what was known at first. What should also be noted in this collection is the Twitter public list compiled by @globeandmail, which showcases tweets surrounding the shooting, and the memorial process afterwards.

Another example of this collection's focus on education. Contains both content for students, and lesson plans for teachers. Gives insight into pedagogy from its extensive lesson plans. Part of a larger series called Aboriginal Youth Identity Series

Representative of this collection's information on First Nation People. An insightful archive for focusing on conceptions of law within aboriginal cultures.It is thorough, and made possible by the efforts of experts.Dense with text, which provides lots of information, but comes at the cost of being less accessible.

Education on Alberta's heritage during the war. Includes excepts from home front documents (such as newsletters to children).

Remove

Remove

Add back in

Add back

Add Links to Live API PResentation https://www.youtube.com/watch?v=Og1EjNaQtgw

https://community.canvaslms.com/servlet/JiveServlet/download/1556-1-95408/LindyFoster.pdf

Remove

Remove sub admins can't add developer keys

This needs to be broken out

Should this be a required reading. Just nested in text now

Remove

Change to Learn@UW

the transition

Remove comma

Have an awareness of Canvas Admin Wiki and be able to find guidelines, updates, and admin practices.

Not only news media, but personal stories being published and saved. Individuals tend to be left out of many narratives around Indigenous rights in Canada, and Residential Schools.

Many different facets of Truth and Reconciliation. This collection shows that it's not just about Residential Schools - though they are the most widely known aspect of it.

This will be an interesting archive to watch. It's an event, but an ongoing event. Historians can track the effects of the Truth and Reconciliation commission and use this archive as a case study for one part of Canada.

Also archiving the fall out of this event. Changes that were made. Addressing public concerns and update the public on the outcomes of those efforts.

Archiving material related to a specific event. What makes an event important enough to archive? Since these records were created while the event was occurring, how is it determined that an event should be actively archived?

Seems an interesting thing to have, but no captures? Why? Is it a matter of crawling difficulties or something else?

None of the collections have been archived more than twice. While there is potential for this collection, its uses are limited to events before the archived date.

Archiving change over time from a non-mainstream source. Offers different points of view about events that could be useful to flesh out arguments.

Earliest date archived, and only archived once.

Another example of this collection's focus on Alberta's heritage. This archive's topic of volunteers provides an insightful look at social and local history.

Not only is it useful for showing Alberta's natural history, but it is also a great example of a website being used for educational purposes. Although the site includes multimedia files, many can't be accessed or played.

A unique collection that showcases Alberta's history through an exhaustive list of patents. Definitely useful for many areas of history: local, social, cultural, technological.

Rich source on history of Alberta radio and culture. The files of audio clips are dead, but the information on the website is still plentiful.

Many of the pages include social media sites used to spread news, opinions, and plans. It makes this event an example of how social media - such as youtube, twitter, and facebook - can spread the word about important issues from sources other than news reporters and gives a voice directly to actors involved in the dispute rather than information mediated through a secondary source.

Because this is a single even, captures occur much more frequently. This demonstrates that this even was considered important enough to capture and archive as it was happening.

A much smaller and contained collection than some others because it refers to a specific event rather than documenting/archiving changes in particular organization or institution over time.

Also includes programs that start at various levels of education, from a full 12 year program starting at the very earliest levels of education to a 3 year program for senior levels of education.

Education developed not only in the Western model, but including the wisdom, experience, and education models of Indigenous peoples in Alberta.

Bilingual programs not only in both official Canadian languages (as evidenced by the number of French curriculum guides), but in other languages that make up a large portion of Canada's multi-cultural population.

First page in English to have an update. However, this one was only update once.

First site that shows any updates, and was updated frequently in the archived years.

Interesting to note that secondary school curriculum contains courses that are both theoretical and passive as well as practical, active education opportunities.

Primarily, the course guide can provide historians with insights not only into the importance of Aboriginal Studies in Alberta, but also into the history that led to the creation of the education program as well as the major themes considered most important to be learned and passed on.

While there are a great number of captures, there hasn't been an update to the page since its first capture in 2010, which, with the contemporary climate around Indigenous history in Canada and Indigenous rights, suggests that while this is an important topic, it's main themes and concerns may not be providing students with the proper depth of contemporary understanding of the issue.

The preservation not only of education curriculum, but a record of how that curriculum changed in a five year period (between 2010-2015 are the current archive dates) could allow historians to examine how priorities have changed, what is considered important to teach the next generation and the expectations held by teachers and government organizations for the children they are educating.

While all of the pages were captured during the same three day period in 2015, there is still this record of webpages that were created, though they are no longer in use. This creates an archival record of what was considered important not only to publish in the first place, but was also acknowledged as important to preserve.