BuboFlash - helps with learning

Edited, memorised or added to reading queue

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Flashcard 4356821617932

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356826598668

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356831579404

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356836560140

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356841540876

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356846521612

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356855172364

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356860153100

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356865133836

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4356870901004

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4357022420236

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4360512867596

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4361745206540

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4361750187276

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4361755168012

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4361760148748

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Flashcard 4361769585932

Tags

#bones #bony #femur #has-images #landmarks

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Annotation 4361824898316

Not all debt is bad, but all debt needs to be [...]

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Annotation 4361828306188

[...] and [...] as an area where ML technical debt may rapidly accumulate

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Flashcard 4361831976204

Question

glue code

Answer

is executable code (often source code) that serves solely to "adapt" different parts of code that would otherwise be incompatible

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Glue code - Wikipedia
e 2016) (Learn how and when to remove this template message) It has been suggested that this article be merged into Glue logic. (Discuss) Proposed since September 2018. In computer programming, <span>glue code is executable code (often source code) that serves solely to "adapt" different parts of code that would otherwise be incompatible. Glue code does not contribute any functionality toward

Flashcard 4361834073356

Question

An example of system-level interactions in ML that leads to tech debt

Answer

chaining of input signals

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Annotation 4361836432652

ML packages may be treated as black boxes, resulting in large masses of [...] or [...] that can lock in assumptions.

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Flashcard 4361838791948

Question

ML is required in exactly those cases when the desired behavior cannot be

Answer

effectively expressed in software logic without dependency on external data .

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Flashcard 4361841151244

Question

CACE principle

Answer

Changing Anything Changes Everything

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Annotation 4361842724108

CACE applies not only to [...] signals, but also to [...] , [...] settings, [...] methods, [...] thresholds, data [...] , and essentially every other possible tweak.

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Flashcard 4361845083404

Question

Entanglement

Answer

Machine learning systems mix signals together , entangling them and making iso- lation of improvements impossible

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Flashcard 4361848491276

Question

Correction Cascades

Answer

There are often situations in which model m_a for problem A exists, but a solution for a slightly different problem A′ is required. In this case, it can be tempting to learn a model m′_a that takes m_a as input and learns a small correction as a fast way to solve the problem

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Flashcard 4361850850572

Question

Undeclared Consumers.

Answer

Oftentimes, a prediction from a machine learning model m_a is made widely accessible, either at runtime or by writing to files or logs that may later be consumed by other systems. Without access controls, some of these consumers may be undeclared, silently using the output of a given model as an input to another system. In more classical software engineering, these issues are referred to as [...]

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Flashcard 4361853209868

Question

Unstable Data Dependencies.

Answer

To move quickly , it is often convenient to consume signals as input features that are produced by other systems. However, some input signals are unstable, meaning that they qualitatively or quantitatively change behavior over time. This can happen implicitly, when the input signal comes from another machine learning model itself that updates over time, or a data-dependent lookup table, such as for computing TF/IDF scores or semantic mappings.

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Annotation 4361855569164

One common mitigation strategy for unstable data dependencies is to create a [...] of a given signal

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Annotation 4361858714892

One possible mitigation strategy is to isolate models and serve [...] . This approach is useful in situations in which [...] such as in disjoint multi-class settings like [14]. However, in many cases [...] work well because the errors in the component models are [...] . Relying on the combination creates a [...] : improving an individual component model may actually make the system accuracy [...] if the [...] are more strongly correlated with the [...] .

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Annotation 4361861074188

A second possible strategy is to focus on detecting changes in [...] behavior as they occur. One such method was proposed in [12], in which a [...] tool was used to allow researchers to quickly see effects across many [...] . Metrics that operate on a [...] basis may also be extremely useful

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Annotation 4361863433484

Mitigation strategies are to [...] m_a to learn the corrections directly within the [...] by [...] features to distinguish among the cases, or to accept the cost of [...] for A′

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Annotation 4361865792780

Undeclared consumers may be difficult to detect unless the system is specifically designed to guard against this case, for example with [...] or [...]

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

pdf

cannot see any pdfs

Flashcard 4361868152076

Question

Underutilized Data Dependencies

Answer

underutilized data dependencies are input signals that provide little incremental modeling benefit.

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

pdf

cannot see any pdfs

Edited, memorised or added to reading queue

on 31-Aug-2019 (Sat)

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf

pdf