| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Moreover, this representation should be task-agnostic.
Yann LeCun · Not checkable · Jun 2023 |
|
| Unresolvable |
Yann LeCun | Prediction |
Jun 2023 |
Regularized methods seem more promising than contrastive methods for training future energy-based models, because they are less likely to fall victim to the curse of dimensionality.
Yann LeCun · Prediction · Jun 2023 |
AI timelines and forecasting |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
However, in decision-making tasks such as driving a car, it is merely necessary that the system chooses the correct answer.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Ideally, the latent variable represents independent explanatory factors of prediction variation.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Therefore, the JEPA can be trained with a loss function that apart from the
Yann LeCun · Not checkable · Jun 2023 |
|
| Unresolvable |
Yann LeCun | Factual |
Jun 2023 |
Ideas related to VICReg-style regularization were explored already in 1992, per reference [62].
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Joint embedding predictive architectures (JEPAs) are a new architecture proposed by LeCun in Ref. [6].
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not researched |
Yann LeCun | Citation |
Jun 2023 |
Normalizing scores in energy-based models runs into the label bias problem (ref. 39), where transition probabilities out of a state are normalized per state rather than globally.
Yann LeCun · Citation · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Moreover, the modern ML systems are very specialized (trained for one task) and brittle (make stupid mistakes).
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Supervised and reinforcement learning dominate modern real-world applications and are highly inefficient compared to human learning.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Mostly true |
Yann LeCun | Factual |
Jun 2023 |
Probabilistic models require normalization and may become intractable for high-dimensional data.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
SSL for images produces blurry predictions.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The key difference is that the world model predicting the future here is learned.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
While the modern large language models sometimes provide an illusion of reasoning, they have no understanding of reality.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
RL works great with games because they can be played over and over in parallel.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Another approach is to add a regularization term that minimizes a certain measure
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Citation |
Jun 2023 |
Score matching (ref. 46) is a regularization technique that minimizes the gradient and maximizes the curvature of the energy landscape around data points.
Yann LeCun · Citation · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Eventually, we hope to achieve a fully autonomous AI, which can perform well on generic tasks by transferring its knowledge and…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The problem of such
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The reason for the limited success of masked AEs in continuous domains like images or videos
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
regularized methods seem more promising for training EBMs of the future.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
All in all, every model that can be multimodal, i.e., have multiple predictions for a single input, is susceptible to collapse.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Negative loglikelihood is then a contrastive method!
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Most large-scale machine learning applications today rely on supervised learning or deep reinforcement learning, which require extreme computational expense.
Yann LeCun · Factual · Jun 2023 |
AI compute, hardware and data |
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Boltzmann machines were fashionable for some time, but the large cost of sampling makes them less useful for real-world applications.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Perhaps surprisingly, this representation encompasses many constrained fitting
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
As of mid-2023, there are no Level 5 self-driving cars, domestic robots, or virtual assistants that learn reliable world models, reason and plan complex action sequences.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
This limitation renders the Hopfield networks less
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
In particular, to prevent the informational energy collapse, we need to make sure that sx and s y carry
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Discrete and continuous Gibbs distribution (or softmax, should be called softargmax):
Yann LeCun · Not checkable · Jun 2023 |
|
| Resolved true |
Yann LeCun | Factual |
Jun 2023 |
LeCun's proposed AI architecture consists of multiple interconnected modules.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Therefore, latent variables enable multiple predictions instead of just one.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
So, we can recast the regularized AE as jointly
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
A promising approach is to combine masked AEs with transformers for images [57].
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
An important thing to note is that the energy function discussed here is used only for inference, not learning.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Thus, they give us a way of handling real-world uncertainty.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Finally, we need to minimize or limit the information content of the latent variable to prevent the model from, e.g., relying solely on…
Yann LeCun · Not checkable · Jun 2023 |
|
| Unresolvable |
Yann LeCun | Prediction |
Jun 2023 |
Contrastive methods are unlikely to lead to future autonomous intelligence because of their unfavorable scaling with data dimension.
Yann LeCun · Prediction · Jun 2023 |
AI timelines and forecasting |
| Mostly true |
Yann LeCun | Factual |
Jun 2023 |
With probabilistic models, training is confined to loss functions derived from the negative log-likelihood, such as cross entropy.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
However, for other architectures, such training may lead to the collapse of the energy function, i.e., given an x the energy landscape…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Therefore, the path to fully autonomous human-like intelligence has three main challenges:
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Low energies should be assigned to compatible pairs of x and y (e.g., slow driving when snow is present) and high energies to incompatible…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
For energy-based models with a continuous y domain, the energy function is smooth and differentiable, allowing gradient-based inference.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Here we summarized the main ideas of LeCun from Ref. [6] that address those limitations.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
The lecture notes summarize the main ideas of the autonomous intelligence architecture proposed by Yann LeCun.
Yann LeCun · Factual · Jun 2023 |
Their own work or organisation |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
In reality, humans imagine most of the outcomes instead of trying them all.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
SSL works very well for text, but for images, models trained to make a single prediction predict the average of all possible predictions.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not researched |
Yann LeCun | Citation |
Jun 2023 |
The method for maximizing information content of learned representations is called variance-invariance-covariance regularization (VICReg), per reference [58].
Yann LeCun · Citation · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The proposed solution to tackle multimodality is latent variable models with joint embeddings, and we discuss them in the next section.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Computing a partition function is very challenging, so probabilistic models in continuous high-dimensional domains are intractable.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The main principle of training an EBM is to sculpt the energy landscape such that data points that are probable or compatible have low…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The global task of this architecture is to take action that minimizes the cost or, even better, minimizes the expected cost in the future.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Such a hierarchical structure allows for multi-level representations of the world and, more
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Some regularized autoencoders learn interpretable features that mirror existing hand-crafted data compression approaches.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The possible approach is designing reasoning and planning as energy minimization.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Finally, latent variables are useful in so-called structured prediction problems.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
The changes of the critic module model the external influence that is provided by culture, norms, and other people.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
A major technique for detecting blacklisted content is nearest-neighbor search against that content.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
In other words, this term decorrelates the representation components, encouraging the learning of different input data aspects.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Therefore, there is no need to use a probabilistic framework, as you just need scores for each situation (word/move, etc.), which in…
Yann LeCun · Not checkable · Jun 2023 |
|
| Mostly true |
Yann LeCun | Factual |
Jun 2023 |
All modules of the proposed architecture are fully differentiable.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
If we train our model only to minimize the distance between the outputs of encoders, then the two encoders are likely to ignore inputs…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Note that the marginal distribution is equivalent to Eq. (A1) in which the energy function has merely been redefined
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
In such high-dimensional and multi-modal real-world setups, we may need to give up the idea of representing probability distributions over…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Maximum likelihood needs to be then regularized, e.g., with Bayesian prior or by limiting values of model parameters.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not researched |
Yann LeCun | Factual |
Jun 2023 |
Current self-driving models need thousands of footage to learn, while humans can learn to drive in about twenty hours.
Yann LeCun · Factual · Jun 2023 |
AI capabilities |
| Unresolvable |
Yann LeCun | Prediction |
Jun 2023 |
Probabilistic models may also fail on the path to autonomous intelligence.
Yann LeCun · Prediction · Jun 2023 |
AI timelines and forecasting |
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
Such an energy-guided model only needs to assign the lowest energy to the correct answer and larger energies to the incorrect ones.
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
In particular, precise predictions of the state of the world, based on the limited percepts of the environment, are possible
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Yann LeCun | Not checkable |
Jun 2023 |
EBMs, which do not have an immediate probabilistic interpretation, give much more flexibility in the choice of the training setup and, in…
Yann LeCun · Not checkable · Jun 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
31 May 2023 |
When a press release about an existential risk for humanity comes from some organization you haven't previously heard of, step 1 is to go…
Rodney Brooks · Not checkable · 31 May 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
28 May 2023 |
Moral: unreliable tools in ordinary hands are dangerous.
Rodney Brooks · Not checkable · 28 May 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
28 May 2023 |
I am just a citizen user of the service.
Rodney Brooks · Not checkable · 28 May 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
28 May 2023 |
Rating: success.
Rodney Brooks · Not checkable · 28 May 2023 |
|
| Own records only |
Rodney Brooks | Factual |
28 May 2023 |
Brooks said that it did not annoy any human drivers.
Rodney Brooks · Factual · 28 May 2023 |
Technology |
| Not checkable |
Jim Cramer | Not checkable |
24 May 2023 |
And we don't know if the psyche of the recently ebullient Chinese consumer will be impacted.
Jim Cramer · Not checkable · 24 May 2023 |
|
| Not checkable |
Jim Cramer | Not checkable |
24 May 2023 |
We don't know if travel will be banned or restricted, although the Macau casino stocks are trading like it's gonna happen
Jim Cramer · Not checkable · 24 May 2023 |
|
| Unresolvable |
Balaji Srinivasan | Prediction |
24 May 2023 |
An extralegal confiscation of private property will take place to remit stolen funds to a cash-hungry federal government, with tech giants described as a "systemic risk" to the crypto industry.
Balaji Srinivasan · Prediction · 24 May 2023 |
Economics and markets |
| Not checkable |
Jim Cramer | Not checkable |
24 May 2023 |
I would hate to advise you to sell and then buy back later, though, because we don't know if you'll be able to get back in before the…
Jim Cramer · Not checkable · 24 May 2023 |
|
| Resolved false |
Jim Cramer | Prediction |
24 May 2023 |
US politicians will cause investors to lose more money as the May 2023 debt ceiling negotiations drag on.
Jim Cramer · Prediction · 24 May 2023 |
Economics and markets |
| Not checkable |
Jim Cramer | Not checkable |
24 May 2023 |
if you think our leaders are serious about making a deal, then it might be worth trying to sidestep the coming decline
Jim Cramer · Not checkable · 24 May 2023 |
|
| Not checkable |
Jim Cramer | Not checkable |
24 May 2023 |
They hurt you then. They aren't done hurting you now.
Jim Cramer · Not checkable · 24 May 2023 |
|
| Mostly true |
Rodney Brooks | Factual |
24 May 2023 |
Brooks described hundreds of driverless cars with no humans inside as driving around San Francisco 'aimlessly' 24 hours a day.
Rodney Brooks · Factual · 24 May 2023 |
Technology |
| Not checkable |
Jim Cramer | Not checkable |
24 May 2023 |
But, unless you trade full-time, it's very hard to get out and get back in early enough for it to make a difference, which means most of us…
Jim Cramer · Not checkable · 24 May 2023 |
|
| Resolved false |
Jim Cramer | Prediction |
24 May 2023 |
If the market follows the 2011 debt ceiling pattern, US stocks will fall about 12% from their level on 2023-05-24 to the bottom.
Jim Cramer · Prediction · 24 May 2023 |
Economics and markets |
| Resolved true |
Jim Cramer | Factual |
24 May 2023 |
In 2011 the US reached a debt ceiling deal, but the standoff led Standard & Poor's to downgrade the US government's credit rating.
Jim Cramer · Factual · 24 May 2023 |
Economics and markets |
| Not checkable |
Balaji Srinivasan | Not checkable |
24 May 2023 |
calls these tech giants a “systemic risk” to the crypto industry
Balaji Srinivasan · Not checkable · 24 May 2023 |
|
| Not checkable |
Marc Andreessen | Not checkable |
19 May 2023 |
We could never have built @a16z without @jeff_jordan -- @bhorowitz and I will always be grateful beyond words to our partner and friend.
Marc Andreessen · Not checkable · 19 May 2023 |
|
| Not checkable |
Jeff Bezos | Not checkable |
19 May 2023 |
Together, we’ll be solving the boil-off problem and making LOX-LH2 a storable propellant combination, pushing forward the state of the art…
Jeff Bezos · Not checkable · 19 May 2023 |
|
| Resolved true |
Jeff Bezos | Factual |
19 May 2023 |
Jeff Bezos is part of a joint effort with NASA to land astronauts on the Moon.
Jeff Bezos · Factual · 19 May 2023 |
Other |
| Not researched |
Rodney Brooks | Factual |
17 May 2023 |
Rodney Brooks gave an interview to IEEE Spectrum editor Glenn Zorpette about a couple of weeks before 17 May 2023, covering GPT and other topics.
Rodney Brooks · Factual · 17 May 2023 |
Their own work or organisation |
| Not checkable |
Marc Andreessen | Not checkable |
8 May 2023 |
🔥 https://t.co/QP348vYv6d
Marc Andreessen · Not checkable · 8 May 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
6 May 2023 |
It irks me when "AI" is used with an article, definite or indefinite
Rodney Brooks · Not checkable · 6 May 2023 |
|
| Unresolvable |
Ray Kurzweil | Prediction |
5 May 2023 |
Parties that agree to a pause in AI research more powerful than GPT-4 may fall far behind corporations or nations that do not.
Ray Kurzweil · Prediction · 5 May 2023 |
AI policy and governance |
| Resolved true |
Ray Kurzweil | Factual |
5 May 2023 |
Kurzweil did not sign the open letter calling for a pause on AI more powerful than GPT-4.
Ray Kurzweil · Factual · 5 May 2023 |
AI policy and governance |
| Not checkable |
Rodney Brooks | Not checkable |
1 May 2023 |
Chatbots have plenty of gall when it comes to facts.
Rodney Brooks · Not checkable · 1 May 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
30 Apr 2023 |
The opposite of all these are true for robocars.
Rodney Brooks · Not checkable · 30 Apr 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
30 Apr 2023 |
Innovation at a distance!!!
Rodney Brooks · Not checkable · 30 Apr 2023 |
|
| Not checkable |
Rodney Brooks | Not checkable |
30 Apr 2023 |
A personned vehicle stopped on Gough St is not 100% equivalent.
Rodney Brooks · Not checkable · 30 Apr 2023 |
|
| Not researched |
Rodney Brooks | Factual |
26 Apr 2023 |
On a morning in late April 2023 a driverless Cruise car stopped with hazard lights on Gough St in San Francisco, blocking one of three lanes while another lane was blocked by construction.
Rodney Brooks · Factual · 26 Apr 2023 |
Technology |